Model data and methodology
How current the data is, how every estimate is computed, and what the site does not claim.
Data status
The only place where freshness is stated; app pages carry no status blocks.
2 of 4 sources use a saved copy. When a source fails, the Wizard keeps the last valid data and says so here.
- Quality benchmark (LiveBench)
- Using saved copy from 2026-10-18LiveBench 2026-06-25 · checked 2026-11-19 · valid as of 2026-10-18source
- Model inventory (Hugging Face)
- Currentchecked 2026-11-19 · valid as of 2026-11-19source
- Hardware specifications
- Currentchecked 2026-11-14 · valid as of 2026-11-14source
- Prices and stock
- Using saved copy from 2026-09-22checked 2026-11-19 · valid as of 2026-09-22 · saved copy: RTX 5090, DGX Sparksource
Memory formulas
Every memory number on the site is an estimate from one of these, or a publisher's documented figure.
New to local AI? Local AI basics: parameters, Q4 and memory, explained with examples
Text models · Q4 planning estimate
Used for every memory column, chart and “runs on” list, in Models, Discover, Compare and the hardware profiles.
memory = ceil( parameters × 0.625 × 1.2 + reserve )- parameters
- Billions of parameters, as the publisher states them or as counted from the repository's floating-point tensors. For mixture-of-experts models, all experts count; active parameters do not shrink the weights you store.
- 0.625
- Bytes per parameter for a 4-bit file with its quantization scales (about 5 bits). A planning constant, not the size of any one file.
- 1.2
- A 20% working allowance for activations and batch buffers.
- reserve
- 25% of unified memory or system RAM for the system (operating system, apps), at least 2 GB and at most 8 GB: 8 GB → 2, 16 GB → 4, 24 GB → 6, 32 GB or more → 8. On a dedicated GPU, 2 GB per card. Without a chosen machine, Models, Discover and Compare show the 8 GB figure (a 32 GB or larger machine).
- Fit tiers
- Runs well: the estimate fits the fast memory (graphics card VRAM, or unified memory within the macOS default GPU share of about 75% plus the reserve).
- Runs slowly: within the machine's memory but outside the fast part; a graphics card runs the layers that do not fit on the CPU from PC RAM, up to VRAM + RAM − the RAM's reserve (the listed RAM, or 32 GB assumed when a card has none listed).
- Doesn't run: above both.
- Hardware tables mark a model that runs well but leaves less than 10% of the fast memory (at least 1 GB) free beyond the reserve as a tight fit, and list it after the models with room to spare.
- A tier is a planning estimate, never a speed.
- Not included
- The KV cache that grows with the context window, vision or audio components, and runtime overhead. The estimate is a floor for planning, not a measured requirement.
- Example
- 27 × 0.625 × 1.2 + 8 = 28.25 rounded up: 29 GB · on 16 GB: 27 × 0.625 × 1.2 + 4 = 24.25 → 25 GBA 27B model on a 32 GB and a 16 GB machine
Q8 and FP16 · the custom-machine planner
Hardware › “Different hardware? Plan a custom machine”. It splits the estimate into parts you can adjust.
weights = parameters × bytes[Q4 0.625 | Q8 1.125 | FP16 2]
memory = ceil( weights + 20% × weights + cache + reserve )- bytes
- Bytes per parameter by weight precision: Q4 0.625, Q8 1.125, FP16 2.
- 20% × weights
- The same working allowance, now a separate line you can see.
- cache
- A budget in GB that you enter. It is not calculated from the context length, because the cache depends on the architecture.
- reserve
- Automatic: 25% of the planned unified or system memory (2 to 8 GB); 2 GB per dedicated GPU. A value you type overrides it.
- Example
- 27B · Q4 29 GB · Q8 45 GB · FP16 73 GBUnified memory of 32 GB or more (8 GB reserve), no extra cache
Embedding models · 8-bit estimate with a small reserve
An encoder has no growing chat cache, so the chat reserve would overstate it (data v2).
memory = ceil( parameters × 1 × 1.2 + 2 )- 1
- Bytes per parameter: 8-bit weights, between the 16-bit small embedders and the 4-bit large ones that runtimes ship.
- 1.2
- The same 20% working allowance.
- 2 GB reserve
- Runtime process plus desktop headroom. A planning assumption: no embedder was benchmarked on hardware, and very long inputs (32K tokens) need more.
- Publisher figure
- When a publisher states its own memory (for example under 200 MB), it is shown separately and never replaces the estimate.
- Example
- 0.74 × 1 × 1.2 + 2 = 2.89 rounded up: 3 GBA 0.74B encoder
Image, video and audio models · documented minimums, then a 16-bit estimate
First the lowest GPU memory a publisher documents, with its platform (CUDA or Apple MPS) and whether the path is direct or conditional (offload, quantization). A published requirement above a machine's memory moves the model to the next tier. A documented path on one platform is never carried to another.
When nothing is documented for the machine's platform, hardware pages show a planning estimate from the published parameter count, labelled “16-bit est.”. Resolution, frame count, text encoders and offload change the real requirement.
memory = ceil( parameters × 2 × 1.2 + 2 )Evidence words
Four words, used the same way on every page.
- Published
- A number or fact a publisher or benchmark states, shown with its source and date: a LiveBench score, a parameter count, a context length, a license, a documented GPU memory.
- Estimated
- Computed here from published inputs with a formula above: memory and disk. A planning guide, never a test and never a compatibility promise.
- Measured
- A result from a named run: hardware, runtime, build, quantization, prompt and output length. Shown exactly as published, never normalized or ranked across setups. Today these are tokens per second from llama.cpp scoreboards and benchmark pages, the mlx-lm benchmark table and a few vendor posts. A machine can also show a “Same chip” reference row: a run on another machine with the same chip and the same memory size, named in the row and never presented as a run on this machine.
- Not measured
- Nothing is published for that checkpoint or hardware. It appears as a dash with the reason, never as zero and never filled in from a neighbor: a reference row comes only from the same chip with the same memory size, never from a different chip, memory size or model.
What we do not claim
- That a model runs on your machine
- “Fits” compares a memory estimate with a memory size. It is not a compatibility test and says nothing about speed.
- Local speed from a score or a spec
- Benchmark scores and memory bandwidth do not predict tokens per second. Speed appears only when someone measured it.
- Quality of a quantized file
- LiveBench scores the publisher's checkpoint, not the Q4 or Q8 build you would download.
- A score where there is none
- A model missing from a benchmark release has no score; it is not zero. Scores from different benchmarks or modalities are never merged into one index. LiveBench has scored no open model below about 27 B parameters since its 2025-04-25 table; older tables use six categories and another question set, so they are not mixed in. Models that fit 8–16 GB therefore have no LiveBench score (current table).Checked 2026-10-10 across every published LiveBench table
- Current prices
- A price appears only as an observed offer with its date, seller and condition, and goes stale after 7 days. Launch prices are labelled historical.
- Advice
- Nothing here is purchase, legal or licensing advice. Licenses belong to their publishers; read them before use.
Rights
Whose scores, pictures and weights appear here, and under what terms.
Attribution and reuse by source
- Artificial Analysis
- Excluded: its free tier allows internal use only. No Artificial Analysis number appears anywhere; pages link to its site.checked 2026-09-22
- LMArena
- CC BY 4.0, attributed on every chart and table that shows a rating. Ratings: Arena (lmarena-ai) text leaderboard, overall, in its default view that adjusts ratings for answer length and formatting, published 2026-10-22, from the Hugging Face dataset lmarena-ai/leaderboard-dataset, licensed under CC BY 4.0. Modified by Local AI Wizard: selected rows only, model names matched to our catalog, ratings rounded. Not endorsed by Arena. Ratings: Arena (lmarena-ai) vision leaderboard, overall, in its default view that adjusts ratings for answer length and formatting, published 2026-10-19, from the Hugging Face dataset lmarena-ai/leaderboard-dataset, licensed under CC BY 4.0. Modified by Local AI Wizard: selected rows only, model names matched to our catalog, ratings rounded. Not endorsed by Arena. Ratings: Arena (lmarena-ai) text-to-image leaderboard, overall, published 2026-10-07, from the Hugging Face dataset lmarena-ai/leaderboard-dataset, licensed under CC BY 4.0. Modified by Local AI Wizard: selected rows only, model names matched to our catalog, ratings rounded. Not endorsed by Arena. Ratings: Arena (lmarena-ai) text-to-video leaderboard, overall, published 2026-09-22, from the Hugging Face dataset lmarena-ai/leaderboard-dataset, licensed under CC BY 4.0. Modified by Local AI Wizard: selected rows only, model names matched to our catalog, ratings rounded. Not endorsed by Arena.
- Open ASR Leaderboard
- Apache-2.0: the word error rates come from the results file in the leaderboard's GitHub repository, which carries the repository's Apache-2.0 licence. The Hub results dataset and the Space declare no licence and are not read. Word error rates: Open ASR Leaderboard (Hugging Face Audio team and contributors), English short-form results file scripts/data/en_shortform.csv of github.com/huggingface/open_asr_leaderboard, version 16743c6 of 2026-05-22 (results stated as of 2026-03-26), licensed under Apache-2.0. Modified by Local AI Wizard: selected rows only, model names matched to our catalog, values rounded. Not endorsed by Hugging Face.
- Music Arena
- MIT leaderboard files computed from a CC BY 4.0 vote dataset. Rating: Music Arena (CMU G-CLef) instrumental leaderboard of 2026-07-31, github.com/gclef-cmu/music-arena (MIT; Copyright (c) 2025 Carnegie Mellon University, Music Arena Team, Chris Donahue), computed from the Music Arena Dataset (CC BY 4.0). Modified by Local AI Wizard: selected rows only, model names matched to our catalog. Not endorsed by Music Arena.
- Hardware pictures
- Only permitted generated images and reviewed manufacturer reference images, each with its caption. A missing or failed image becomes a labelled illustration.
- Models and weights
- Each model keeps its publisher's license, shown with a link to the license text. The site republishes facts and links, not weights.
Sources and dates
Collection date, benchmark release and page publication are different dates; each is labelled.
Every source, with collection date
- LiveBench
- Quality scores for text models, with seven category means.release 2026-06-25 · collected 2026-10-18
- LMArena
- Text leaderboard ratings (overall, in the default "style control" view, which adjusts ratings for answer length and formatting) for the open models matched by hand review, with interval and votes; read from the public Hugging Face dataset, never from the site. A rating is blind pairwise human preference on the hosted model, not a test of a quantized local file and not task success; it has its own scale, shown in its own lens and column, and is never merged with, converted to or ranked against LiveBench. Some models below 27 B have a rating; a model with no Arena entry has none, never a sibling's.release 2026-10-22 · collected 2026-10-25
- LMArena · vision, image, video
- One leaderboard per category, each read from the same CC BY 4.0 Hugging Face dataset: vision (style control, overall) for the image-understanding models on Models › Vision, text-to-image (overall) for image generation, and text-to-video (overall) for video. Identity comes only from a reviewed map per category with one exact name per repository or catalog entry: base, quantized, distilled, preset and effort variants never take a rating. Inside a category every compared model comes from the same board and release; boards are never merged with each other, with the text board or with publisher metrics. Video matches only two of our models, so its rating is a fact on those two pages and is not ranked. Wan's VBench numbers are publisher-reported and are not ranked against other models either.vision 2026-10-19 · image 2026-10-07 · video 2026-09-22 · collected 2026-10-25
- Audio quality
- Audio has no single score: speech to text, text to speech and music are separate quality slots, each judged by its own test on its own scale, never merged. Speech to text: the Open ASR Leaderboard word error rate (English short-form, macro-average of eight test sets; lower is better). Music: the Music Arena instrumental rating, a fact on the one model it covers. Text to speech: no board publishes its results under a licence, so no score.Open ASR 2026-05-22 · Music Arena 2026-07-31
- Hugging Face Hub
- Model inventory: tasks, licenses, parameter counts, files, downloads.bundled copy 2026-09-26 · live status above
- GenEval · VBench
- Published image and video results for the few models they cover. VBench comes from the Wan authors' own report: publisher-reported, shown on those model pages and never ranked against other models.observed 2026-10-20
- Apple and NVIDIA product pages
- Memory specifications of the hardware profiles, plus each profile's own sourced fields.memory checked 2026-09-30 · profiles reviewed 2026-09-30
- llama.cpp
- Community llama-bench scoreboards (CUDA, ROCm, Apple Silicon, Vulkan) and the repository’s own benches/ pages: measured speeds, copied as published.scoreboards checked 2026-10-25 · benches/ commit 2280f0f · checked 2026-10-25
- mlx-lm
- The maintainers’ benchmark table (mlx_lm/BENCHMARKS.md, MIT license): generation tokens per second on an Apple M4 Max for each MLX precision.commit 4cfc647 · checked 2026-10-25
- Steam Hardware Survey
- Only the order of graphics cards in the hardware catalog. Not sales and not local-AI use.August 2026
- Publisher-reported results
- Benchmark numbers each publisher prints on its own model card (the card's model-index and evaluation tables), copied as printed with their benchmark variant, unit, shots, thinking mode and harness when stated, and a link to the card. They are a different kind of evidence from the independent scores above: LiveBench, LMArena and MTEB run the same test for every model they cover, while a publisher chooses its own prompts, settings and comparison models. So publisher-reported values are shown only as facts on the model page, under "Reported by the publisher"; they never fill a comparable-score column, chart or ranking, and are never compared across publishers. Sizes of one family stand side by side only when the publisher reports them in the same card section with the same settings. A card with no numbers is recorded as not published; a gated card stays unread.cards read 2026-10-26
- Model cards
- The reviewed catalog links each checkpoint to its official card.catalog reviewed 2026-09-30
Downloads and fields
This curated table selects 260 checkpoints with primary model cards. IDs are stable within this catalog. The dynamic Wizard may show newer D1 data; these static files remain dated until editorial review and publication.
Of 60 selected language checkpoints, 36 fall at or below 32 GB and 37 at or below 64 GB under the same generic Q4 planning formula. 5 has no defensible simplified estimate. These are counts of this curated sample, not successful local runs or a census of all open models. Reproduce by filtering the JSON on task = language and reasoning, then counting non-null memoryEstimateGB at each threshold.
Fields and units
- id
- Stable catalog slug, not the publisher repository identifier.
- parametersB / parameterBasis
- Billions of stated model parameters or repository tensor elements, as qualified by the basis field; null when not verified. Auxiliary components may be separate.
- score / scoreStatus
- LiveBench overall 0–100 for language and MTEB (Multilingual, v2) mean(task) 0–100 for embeddings, never mixed: scoreLabel names the scale, vector size and who measured it. Artificial Analysis media scores are excluded because its free tier is internal use only; scoreStatus explains the excluded values and scoreSource links to the original scale.
- memoryEstimateGB
- Generic Q4 planning estimate in decimal GB for selected language checkpoints; not measured VRAM. Null means unknown or an inapplicable simplified formula.
- repositoryStorageGB
- Full published repository size where verified. It may include multiple formats and is not the minimum download.
Reviewed checkpoints
| ID / model | Modality | Quality evidence | Source |
|---|---|---|---|
| Qwen3.5 9B qwen3.5-9b | text + image + video | — | model card |
| Qwen3.8 27B qwen3.8-27b | text + image + video | 75.3 · LiveBench 2026-06-25 overall | model card |
| Qwen3.5 35B A3B qwen3.5-35b-a3b | text + image + video | — | model card |
| Qwen3.6 27B qwen3.6-27b | text + image + video | 64 · LiveBench 2026-06-25 overall | model card |
| Smaug Mini smaug-mini | text + image | 76.9 · LiveBench 2026-06-25 overall | model card |
| DeepSeek V4 Flash · 0731 deepseek-v4-flash-0731 | text | 74.2 · LiveBench 2026-06-25 overall | model card |
| GLM-5.3 Flash glm-5.3-flash | text + image | 71.6 · LiveBench 2026-06-25 overall | model card |
| GLM-5.3 glm-5.3 | text | 76.1 · LiveBench 2026-06-25 overall | model card |
| Kimi K2.6 · thinking kimi-k2.6-thinking | text + image | 70.5 · LiveBench 2026-06-25 overall | model card |
| DeepSeek V4.1 Flash · max deepseek-v4.1-flash-max | text + image | 81.1 · LiveBench 2026-06-25 overall | model card |
| DeepSeek V4 Flash deepseek-v4-flash | text | 65.5 · LiveBench 2026-06-25 overall | model card |
| DeepSeek V4 Pro deepseek-v4-pro | text | 71.6 · LiveBench 2026-06-25 overall | model card |
| GLM-5.2 glm-5.2 | text | 73.2 · LiveBench 2026-06-25 overall | model card |
| Kimi K2.7 Code kimi-k2.7-code | text + image | 68.4 · LiveBench 2026-06-25 overall | model card |
| MiniMax M3 minimax-m3 | text + image + video | 67.3 · LiveBench 2026-06-25 overall | model card |
| Kimi K3 kimi-k3 | text + image | 79.2 · LiveBench 2026-06-25 overall | model card |
| Inkling · xhigh inkling-xhigh | text + image + audio | 71.9 · LiveBench 2026-06-25 overall | model card |
| Qwen3.8 Max qwen3.8-max | text | 78.5 · LiveBench 2026-06-25 overall | model card |
| Smaug Agentic smaug-agentic | text + image | 79.5 · LiveBench 2026-06-25 overall | model card |
| DeepSeek V4 Pro · 0813 deepseek-v4-pro-0813 | text | 77.4 · LiveBench 2026-06-25 overall | model card |
| DeepSeek V4 Flash Vision · exp deepseek-v4-flash-vision-exp | text + image | 76.8 · LiveBench 2026-06-25 overall | model card |
| Qwen3.8 Flash Next qwen3.8-flash-next | text + image + video | 76.2 · LiveBench 2026-06-25 overall | model card |
| Nemotron 3 Ultra 550B A55B nemotron-3-ultra-550b-a55b | text | 67.4 · LiveBench 2026-06-25 overall | model card |
| Smaug Flash smaug-flash | text | 77.4 · LiveBench 2026-06-25 overall | model card |
| Nemotron 3 Super 120B A12B nemotron-3-super-120b-a12b | text | — | model card |
| MiMo V2.6 Pro mimo-v2.6-pro | text + image + video + audio | — | model card |
| MiMo V2.6 Flash mimo-v2.6-flash | text + image + video + audio | — | model card |
| Ling 3.0 Flash ling-3.0-flash | text | — | model card |
| FLUX.2 [dev] flux-2-dev | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Qwen-Image qwen-image | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Wan2.1 T2V 1.3B wan2.1-t2v-1.3b | video | — | model card |
| Stable Audio Open Small stable-audio-open-small | audio | — | model card |
| FLUX.1 [dev] flux-1-dev | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| FLUX.1 [schnell] flux-1-schnell | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| HunyuanImage-2.1 hunyuanimage-2.1 | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Ideogram 4.0 ideogram-4 | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Qwen-Image-2512 qwen-image-2512 | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Stable Diffusion 3.5 Large stable-diffusion-3.5-large | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Wan2.1 T2V 14B wan2.1-t2v-14b | video | — | model card |
| Wan2.2 T2V-A14B wan2.2-t2v-a14b | video | — | model card |
| CogVideoX-5B cogvideox-5b | video | — | model card |
| HunyuanVideo hunyuanvideo | video | — | model card |
| LTX-Video 2B · 0.9.8 distilled ltx-video-2b-0.9.8-distilled | video | — | model card |
| Whisper large-v3 whisper-large-v3 | audio | — | model card |
| Whisper large-v3-turbo whisper-large-v3-turbo | audio | — | model card |
| Stable Audio Open 1.0 stable-audio-open-1.0 | audio | — | model card |
| MusicGen Small musicgen-small | audio | — | model card |
| Gemma 4 E2B gemma-4-e2b | text + image + audio + video | — | model card |
| Gemma 4 E4B gemma-4-e4b | text + image + audio + video | — | model card |
| Gemma 4 12B gemma-4-12b | text + image + audio + video | — | model card |
| Gemma 4 26B A4B gemma-4-26b-a4b | text + image | — | model card |
| Gemma 4 31B gemma-4-31b | text + image | — | model card |
| EmbeddingGemma 2 embeddinggemma-2 | text + image + video + audio | 61.4 · MTEB (Multilingual, v2) mean(task) · 768d · publisher-reported | model card |
| EmbeddingGemma (300M) embeddinggemma-300m | text | 61.1 · MTEB (Multilingual, v2) mean(task) · 768d · independent run | model card |
| Qwen3-Embedding 0.6B qwen3-embedding-0.6b | text | 64.3 · MTEB (Multilingual, v2) mean(task) · 1024d · independent run | model card |
| Qwen3-Embedding 4B qwen3-embedding-4b | text | 69.5 · MTEB (Multilingual, v2) mean(task) · 2560d · independent run | model card |
| Qwen3-Embedding 8B qwen3-embedding-8b | text | 70.6 · MTEB (Multilingual, v2) mean(task) · 4096d · independent run | model card |
| BGE-M3 bge-m3 | text | 59.6 · MTEB (Multilingual, v2) mean(task) · 1024d · independent run | model card |
| Nomic Embed Text v2 (MoE) nomic-embed-text-v2-moe | text | 57.6 · MTEB (Multilingual, v2) mean(task) · 768d · independent run | model card |
| Granite Embedding 278M Multilingual granite-embedding-278m-multilingual | text | 53.7 · MTEB (Multilingual, v2) mean(task) · 768d · independent run | model card |
| Granite Embedding 311M Multilingual R2 granite-embedding-311m-multilingual-r2 | text | 56 · MTEB (Multilingual, v2) mean(task) · 768d · independent run | model card |
| Multilingual E5 Large Instruct multilingual-e5-large-instruct | text | 63.2 · MTEB (Multilingual, v2) mean(task) · 1024d · independent run | model card |
| Multilingual E5 Base multilingual-e5-base | text | 57 · MTEB (Multilingual, v2) mean(task) · 768d · independent run | model card |
| Snowflake Arctic Embed L v2.0 snowflake-arctic-embed-l-v2.0 | text | 57 · MTEB (Multilingual, v2) mean(task) · 1024d · independent run | model card |
| BGE Small EN v1.5 bge-small-en-v1.5 | text | 43.8 · MTEB (Multilingual, v2) mean(task) · 384d · independent run | model card |
| BGE Base EN v1.5 bge-base-en-v1.5 | text | 44.5 · MTEB (Multilingual, v2) mean(task) · 768d · independent run | model card |
| BGE Large EN v1.5 bge-large-en-v1.5 | text | 45.1 · MTEB (Multilingual, v2) mean(task) · 1024d · independent run | model card |
| Granite Embedding Small English R2 granite-embedding-small-english-r2 | text | No MTEB result with a source for this model. | model card |
| Llama Nemotron Embed 1B v2 llama-nemotron-embed-1b-v2 | text | No MTEB result with a source for this model. | model card |
| BGE Multilingual Gemma2 bge-multilingual-gemma2 | text | No MTEB result with a source for this model. | model card |
| Harrier OSS v1 (0.6B) harrier-oss-v1-0.6b | text | 69 · MTEB (Multilingual, v2) mean(task) · 1024d · independent run | model card |
| Nemotron 3 Embed 1B nemotron-3-embed-1b-bf16 | text | No MTEB result with a source for this model. | model card |
| Qwen3 1.7B qwen3-1.7b | text | — | model card |
| Qwen3 4B Instruct 2507 qwen3-4b-instruct-2507 | text | — | model card |
| Qwen3 8B qwen3-8b | text | — | model card |
| Qwen3 14B qwen3-14b | text | — | model card |
| Qwen3 30B A3B Instruct 2507 qwen3-30b-a3b-instruct-2507 | text | — | model card |
| Qwen3 Coder 30B A3B qwen3-coder-30b-a3b | text | — | model card |
| gpt-oss-20b gpt-oss-20b | text | — | model card |
| Llama 3.1 8B Instruct llama-3.1-8b-instruct | text | — | model card |
| Llama 3.2 3B Instruct llama-3.2-3b-instruct | text | — | model card |
| Llama 3.2 1B Instruct llama-3.2-1b-instruct | text | — | model card |
| Mistral Small 3.2 24B mistral-small-3.2-24b | text + image | — | model card |
| Ministral 3 3B ministral-3-3b | text + image | — | model card |
| Ministral 3 8B ministral-3-8b | text + image | — | model card |
| Ministral 3 14B ministral-3-14b | text + image | — | model card |
| Devstral Small 2 24B devstral-small-2-24b | text + image | — | model card |
| Granite 4.2 3B granite-4.2-3b | text | — | model card |
| Granite 4.2 8B granite-4.2-8b | text | — | model card |
| Granite 4.2 30B granite-4.2-30b | text | — | model card |
| Olmo 3 7B Instruct olmo-3-7b-instruct | text | — | model card |
| Olmo 3 32B Think olmo-3-32b-think | text | — | model card |
| Phi-4 mini phi-4-mini | text | — | model card |
| Phi-4 phi-4 | text | — | model card |
| SmolLM3 3B smollm3-3b | text | — | model card |
| Nemotron 3 Nano 30B A3B nemotron-3-nano-30b-a3b | text | — | model card |
| Nemotron 3.5 Lightning 30B A3B nemotron-3.5-lightning-30b-a3b | text | — | model card |
| GLM-4.7 Flash glm-4.7-flash | text | — | model card |
| DeepSeek R1 0528 Qwen3 8B deepseek-r1-0528-qwen3-8b | text | — | model card |
| Stable Diffusion XL 1.0 stable-diffusion-xl-1 | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Stable Diffusion 1.5 stable-diffusion-1-5 | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Z-Image Turbo z-image-turbo | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| FLUX.2 [klein] Base 4B flux-2-klein-base-4b | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| FLUX.2 [klein] 4B flux-2-klein-4b | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| FLUX.2 [klein] 9B flux-2-klein-9b | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| FLUX.2 [klein] Base 9B flux-2-klein-base-9b | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Stable Diffusion 3.5 Medium stable-diffusion-3-5-medium | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| HiDream-I1-Fast hidream-i1-fast | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| HunyuanImage 3.0 Instruct (Fal) hunyuanimage-3-instruct | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| FLUX.1 Krea [dev] flux-1-krea-dev | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| LongCat Image longcat-image | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Cosmos3-Super-Text2Image cosmos3-super | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Stable Diffusion 3.5 Large Turbo stable-diffusion-3-5-large-turbo | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| HiDream-O1-Image hidream-o1-image | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| ERNIE Image Turbo ernie-image-turbo | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Bagel bagel | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| GLM-Image glm-image | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| OmniGen V2 omnigen-v2 | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Stable Diffusion 3 Medium stable-diffusion-3-medium | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| ERNIE Image ernie-image | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| HunyuanImage 3.0 (Fal) hunyuanimage-3 | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Lumina Image v2 lumina-image-v2 | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| HiDream-O1-Image-Dev hidream-o1-image-dev | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| FIBO fibo | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| SRPO srpo | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| HiDream-I1-Dev hidream-i1-dev | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Infinity 8B infinity-8b | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Sana Sprint 1.6B sana-sprint-1-6b | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Cosmos3-Super-Text2Image-4Step cosmos3-super-4step | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Janus Pro janus-pro | image | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| MiniMax H3 minimax-h3 | video | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| LTX-2.5 ltx-2-5-pro | video | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| LTX-2.3 ltx-2-3-pro | video | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| LTX-2 ltx-2-pro | video | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Kokoro 82M v1.0 kokoro-82m | audio | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| VibeVoice 1.5B vibevoice-1-5b | audio | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Higgs Audio V3 TTS higgs-audio-v3-tts | audio | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Fish Audio S2 Pro fish-audio-s2-pro | audio | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Breeze TTS 2 breeze-tts-2 | audio | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Magpie-Multilingual 357M magpie-multilingual-357m | audio | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Maya1 maya1 | audio | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| OpenAudio S1 Mini openaudio-s1-mini | audio | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Voxtral TTS voxtral-tts | audio | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Chatterbox chatterbox | audio | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| Zonos-v0.1 zonos-v0-1 | audio | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| MetaVoice v1 metavoice-v1 | audio | Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. | model card |
| vit-base-patch16-224 vit-base-patch16-224 | image + text | — | model card |
| Qwen3-VL-8B-Instruct qwen3-vl-8b-instruct | image + text | — | model card |
| Qwen2.5-VL-7B-Instruct qwen2.5-vl-7b-instruct | image + text | — | model card |
| Qwen3.6-35B-A3B qwen3.6-35b-a3b | image + text | — | model card |
| Qwen3-VL-4B-Instruct qwen3-vl-4b-instruct | image + text | — | model card |
| Qwen3-VL-2B-Instruct qwen3-vl-2b-instruct | image + text | — | model card |
| DeepSeek-OCR deepseek-ocr | image + text | — | model card |
| siglip2-giant-opt-patch16-384 siglip2-giant-opt-patch16-384 | image + text | — | model card |
| GLM-OCR glm-ocr | image + text | — | model card |
| owlv2-base-patch16-ensemble owlv2-base-patch16-ensemble | image + text | — | model card |
| siglip2-base-patch16-224 siglip2-base-patch16-224 | image + text | — | model card |
| chandra-ocr-2 chandra-ocr-2 | image + text | — | model card |
| Unlimited-OCR unlimited-ocr | image + text | — | model card |
| SmolVLM2-500M-Video-Instruct smolvlm2-500m-video-instruct | image + text | — | model card |
| siglip-base-patch16-224 siglip-base-patch16-224 | image + text | — | model card |
| siglip2-base-patch16-naflex siglip2-base-patch16-naflex | image + text | — | model card |
| llava-1.5-7b-hf llava-1.5-7b-hf | image + text | — | model card |
| siglip-so400m-patch14-384 siglip-so400m-patch14-384 | image + text | — | model card |
| siglip2-so400m-patch14-384 siglip2-so400m-patch14-384 | image + text | — | model card |
| Qwen2.5-VL-32B-Instruct qwen2.5-vl-32b-instruct | image + text | — | model card |
| dots.ocr dots.ocr | image + text | — | model card |
| Qwen2-VL-7B-Instruct qwen2-vl-7b-instruct | image + text | — | model card |
| Phi-3.5-vision-instruct phi-3.5-vision-instruct | image + text | — | model card |
| siglip2-base-patch16-256 siglip2-base-patch16-256 | image + text | — | model card |
| LightOnOCR-2-1B lightonocr-2-1b | image + text | — | model card |
| CLIP-ViT-H-14-laion2B-s32B-b79K clip-vit-h-14-laion2b-s32b-b79k | image + text | — | model card |
| InternVL2-2B internvl2-2b | image + text | — | model card |
| GOT-OCR2_0 got-ocr2-0 | image + text | — | model card |
| gemma-4-31B google-gemma-4-31b | image + text | — | model card |
| chandra chandra | image + text | — | model card |
| Qwen3-VL-235B-A22B-Instruct qwen3-vl-235b-a22b-instruct | image + text | — | model card |
| granite-docling-258M granite-docling-258m | image + text | — | model card |
| SmolVLM-256M-Instruct smolvlm-256m-instruct | image + text | — | model card |
| Qwen3-VL-30B-A3B-Instruct qwen3-vl-30b-a3b-instruct | image + text | — | model card |
| MinerU2.5-Pro-2605-1.2B mineru2.5-pro-2605-1.2b | image + text | — | model card |
| dots.mocr dots.mocr | image + text | — | model card |
| granite-vision-3.3-2b granite-vision-3.3-2b | image + text | — | model card |
| UI-TARS-1.5-7B ui-tars-1.5-7b | image + text | — | model card |
| MiniCPM-V-4.6 minicpm-v-4.6 | image + text | — | model card |
| granite-vision-4.1-4b granite-vision-4.1-4b | image + text | — | model card |
| Llama-4-Scout-17B-16E-Instruct llama-4-scout-17b-16e-instruct | image + text | — | model card |
| Phi-4-multimodal-instruct phi-4-multimodal-instruct | image + text | — | model card |
| SmolVLM2-2.2B-Instruct smolvlm2-2.2b-instruct | image + text | — | model card |
| SmolVLM-500M-Instruct smolvlm-500m-instruct | image + text | — | model card |
| Cosmos-Reason2-8B cosmos-reason2-8b | image + text | — | model card |
| GLM-4.6V-Flash glm-4.6v-flash | image + text | — | model card |
| InternVL3-8B internvl3-8b | image + text | — | model card |
| MiniCPM-V-4_5 minicpm-v-4-5 | image + text | — | model card |
| olmOCR-7B-0225-preview olmocr-7b-0225-preview | image + text | — | model card |
| olmOCR-2-7B-1025 olmocr-2-7b-1025 | image + text | — | model card |
| Llama-3.1-Nemotron-Nano-VL-8B-V1 llama-3.1-nemotron-nano-vl-8b-v1 | image + text | — | model card |
| gemma-4-12B google-gemma-4-12b | image + text | — | model card |
| Idefics3-8B-Llama3 idefics3-8b-llama3 | image + text | — | model card |
| granite-4.0-3b-vision granite-4.0-3b-vision | image + text | — | model card |
| llava-onevision-qwen2-7b-ov-hf llava-onevision-qwen2-7b-ov-hf | image + text | — | model card |
| Llama-3.2-11B-Vision-Instruct llama-3.2-11b-vision-instruct | image + text | — | model card |
| Qianfan-OCR qianfan-ocr | image + text | — | model card |
| InternVL3_5-8B internvl3-5-8b | image + text | — | model card |
| SmolVLM2-256M-Video-Instruct smolvlm2-256m-video-instruct | image + text | — | model card |
| Emu3-Chat-hf emu3-chat-hf | image + text | — | model card |
| GLM-4.5V glm-4.5v | image + text | — | model card |
| SmolDocling-256M-preview smoldocling-256m-preview | image + text | — | model card |
| Holo2-4B holo2-4b | image + text | — | model card |
| SmolVLM-Instruct smolvlm-instruct | image + text | — | model card |
| Molmo-7B-D-0924 molmo-7b-d-0924 | image + text | — | model card |
| NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 nvidia-nemotron-nano-12b-v2-vl-bf16 | image + text | — | model card |
| Step3-VL-10B step3-vl-10b | image + text | — | model card |
| Keye-VL-1_5-8B keye-vl-1-5-8b | image + text | — | model card |
| Llama-3.2-11B-Vision llama-3.2-11b-vision | image + text | — | model card |
| kosmos-2.5 kosmos-2.5 | image + text | — | model card |
| MinerU2.5-2509-1.2B mineru2.5-2509-1.2b | image + text | — | model card |
| NVLM-D-72B nvlm-d-72b | image + text | — | model card |
| Molmo-72B-0924 molmo-72b-0924 | image + text | — | model card |
| Llama-4-Maverick-17B-128E-Instruct llama-4-maverick-17b-128e-instruct | image + text | — | model card |
| Mage-VL mage-vl | image + text | — | model card |
| deepseek-vl2 deepseek-vl2 | image + text | — | model card |
| LLaVA-OneVision-1.5-8B-Instruct llava-onevision-1.5-8b-instruct | image + text | — | model card |
| Falcon-OCR falcon-ocr | image + text | — | model card |
| Fara1.5-9B fara1.5-9b | image + text | — | model card |
| Fara-7B fara-7b | image + text | — | model card |
| Phi-4-reasoning-vision-15B phi-4-reasoning-vision-15b | image + text | — | model card |
| Llama-4-Scout-17B-16E llama-4-scout-17b-16e | image + text | — | model card |
| Fara1.5-27B fara1.5-27b | image + text | — | model card |
| Llama-Guard-3-11B-Vision llama-guard-3-11b-vision | image + text | — | model card |
| Youtu-VL-4B-Instruct youtu-vl-4b-instruct | image + text | — | model card |
| Fara1.5-4B fara1.5-4b | image + text | — | model card |
| SmolVLM2-2.2B-Base smolvlm2-2.2b-base | image + text | — | model card |
| MolmoMotion-4B-H1-F32 molmomotion-4b-h1-f32 | image + text | — | model card |
| Youtu-Parsing youtu-parsing | image + text | — | model card |
| tipsv1-g14-lowres tipsv1-g14-lowres | image + text | — | model card |
| nemotron-labs-audio-visual-flamingo-hf nemotron-labs-audio-visual-flamingo-hf | image + text | — | model card |
| Llama-3.2-90B-Vision-Instruct llama-3.2-90b-vision-instruct | image + text | — | model card |
| Keye-VL-2.0-30B-A3B keye-vl-2.0-30b-a3b | image + text | — | model card |
| tipsv1-l14 tipsv1-l14 | image + text | — | model card |
| tipsv1-g14 tipsv1-g14 | image + text | — | model card |
| tipsv1-so400m14 tipsv1-so400m14 | image + text | — | model card |
| Aquila-VL-2B-llava-qwen aquila-vl-2b-llava-qwen | image + text | — | model card |
| POINTS-Reader points-reader | image + text | — | model card |
| Llama-4-Maverick-17B-128E llama-4-maverick-17b-128e | image + text | — | model card |
| Perception-LM-8B perception-lm-8b | image + text | — | model card |
| cogvlm2-llama3-caption cogvlm2-llama3-caption | image + text | — | model card |
| Video-XL-2 video-xl-2 | image + text | — | model card |
| tipsv1-s14 tipsv1-s14 | image + text | — | model card |
| Bunny-v1_1-Llama-3-8B-V bunny-v1-1-llama-3-8b-v | image + text | — | model card |
| tipsv1-b14 tipsv1-b14 | image + text | — | model card |
| Recon2Reason-Reasoning-4B recon2reason-reasoning-4b | image + text | — | model card |
| Llama-3.2-90B-Vision llama-3.2-90b-vision | image + text | — | model card |
| LFM2-VL-1.6B lfm2-vl-1.6b | image + text | — | model card |
| LFM2.5-VL-1.6B lfm2.5-vl-1.6b | image + text | — | model card |
| ERNIE-4.5-VL-28B-A3B-PT ernie-4.5-vl-28b-a3b-pt | image + text | — | model card |
| diffusiongemma-26B-A4B-it diffusiongemma-26b-a4b-it | image + text | — | model card |
| North-Micro-Vision-Instruct north-micro-vision-instruct | image + text | — | model card |
| Apriel-1.6-15b-Thinker apriel-1.6-15b-thinker | image + text | — | model card |
| surya-ocr-2 surya-ocr-2 | image + text | — | model card |
Directory
Every reviewed page, each with its source, date and limits.
Models 260
Reviewed model profiles
All 260 reviewed models
- Qwen3.5 9B
- Qwen3.8 27B
- Qwen3.5 35B A3B
- Qwen3.6 27B
- Smaug Mini
- DeepSeek V4 Flash · 0731
- GLM-5.3 Flash
- GLM-5.3
- Kimi K2.6 · thinking
- DeepSeek V4.1 Flash · max
- DeepSeek V4 Flash
- DeepSeek V4 Pro
- GLM-5.2
- Kimi K2.7 Code
- MiniMax M3
- Kimi K3
- Inkling · xhigh
- Qwen3.8 Max
- Smaug Agentic
- DeepSeek V4 Pro · 0813
- DeepSeek V4 Flash Vision · exp
- Qwen3.8 Flash Next
- Nemotron 3 Ultra 550B A55B
- Smaug Flash
- Nemotron 3 Super 120B A12B
- MiMo V2.6 Pro
- MiMo V2.6 Flash
- Ling 3.0 Flash
- FLUX.2 [dev]
- Qwen-Image
- Wan2.1 T2V 1.3B
- Stable Audio Open Small
- FLUX.1 [dev]
- FLUX.1 [schnell]
- HunyuanImage-2.1
- Ideogram 4.0
- Qwen-Image-2512
- Stable Diffusion 3.5 Large
- Wan2.1 T2V 14B
- Wan2.2 T2V-A14B
- CogVideoX-5B
- HunyuanVideo
- LTX-Video 2B · 0.9.8 distilled
- Whisper large-v3
- Whisper large-v3-turbo
- Stable Audio Open 1.0
- MusicGen Small
- Gemma 4 E2B
- Gemma 4 E4B
- Gemma 4 12B
- Gemma 4 26B A4B
- Gemma 4 31B
- EmbeddingGemma 2
- EmbeddingGemma (300M)
- Qwen3-Embedding 0.6B
- Qwen3-Embedding 4B
- Qwen3-Embedding 8B
- BGE-M3
- Nomic Embed Text v2 (MoE)
- Granite Embedding 278M Multilingual
- Granite Embedding 311M Multilingual R2
- Multilingual E5 Large Instruct
- Multilingual E5 Base
- Snowflake Arctic Embed L v2.0
- BGE Small EN v1.5
- BGE Base EN v1.5
- BGE Large EN v1.5
- Granite Embedding Small English R2
- Llama Nemotron Embed 1B v2
- BGE Multilingual Gemma2
- Harrier OSS v1 (0.6B)
- Nemotron 3 Embed 1B
- Qwen3 1.7B
- Qwen3 4B Instruct 2507
- Qwen3 8B
- Qwen3 14B
- Qwen3 30B A3B Instruct 2507
- Qwen3 Coder 30B A3B
- gpt-oss-20b
- Llama 3.1 8B Instruct
- Llama 3.2 3B Instruct
- Llama 3.2 1B Instruct
- Mistral Small 3.2 24B
- Ministral 3 3B
- Ministral 3 8B
- Ministral 3 14B
- Devstral Small 2 24B
- Granite 4.2 3B
- Granite 4.2 8B
- Granite 4.2 30B
- Olmo 3 7B Instruct
- Olmo 3 32B Think
- Phi-4 mini
- Phi-4
- SmolLM3 3B
- Nemotron 3 Nano 30B A3B
- Nemotron 3.5 Lightning 30B A3B
- GLM-4.7 Flash
- DeepSeek R1 0528 Qwen3 8B
- Stable Diffusion XL 1.0
- Stable Diffusion 1.5
- Z-Image Turbo
- FLUX.2 [klein] Base 4B
- FLUX.2 [klein] 4B
- FLUX.2 [klein] 9B
- FLUX.2 [klein] Base 9B
- Stable Diffusion 3.5 Medium
- HiDream-I1-Fast
- HunyuanImage 3.0 Instruct (Fal)
- FLUX.1 Krea [dev]
- LongCat Image
- Cosmos3-Super-Text2Image
- Stable Diffusion 3.5 Large Turbo
- HiDream-O1-Image
- ERNIE Image Turbo
- Bagel
- GLM-Image
- OmniGen V2
- Stable Diffusion 3 Medium
- ERNIE Image
- HunyuanImage 3.0 (Fal)
- Lumina Image v2
- HiDream-O1-Image-Dev
- FIBO
- SRPO
- HiDream-I1-Dev
- Infinity 8B
- Sana Sprint 1.6B
- Cosmos3-Super-Text2Image-4Step
- Janus Pro
- MiniMax H3
- LTX-2.5
- LTX-2.3
- LTX-2
- Kokoro 82M v1.0
- VibeVoice 1.5B
- Higgs Audio V3 TTS
- Fish Audio S2 Pro
- Breeze TTS 2
- Magpie-Multilingual 357M
- Maya1
- OpenAudio S1 Mini
- Voxtral TTS
- Chatterbox
- Zonos-v0.1
- MetaVoice v1
- vit-base-patch16-224
- Qwen3-VL-8B-Instruct
- Qwen2.5-VL-7B-Instruct
- Qwen3.6-35B-A3B
- Qwen3-VL-4B-Instruct
- Qwen3-VL-2B-Instruct
- DeepSeek-OCR
- siglip2-giant-opt-patch16-384
- GLM-OCR
- owlv2-base-patch16-ensemble
- siglip2-base-patch16-224
- chandra-ocr-2
- Unlimited-OCR
- SmolVLM2-500M-Video-Instruct
- siglip-base-patch16-224
- siglip2-base-patch16-naflex
- llava-1.5-7b-hf
- siglip-so400m-patch14-384
- siglip2-so400m-patch14-384
- Qwen2.5-VL-32B-Instruct
- dots.ocr
- Qwen2-VL-7B-Instruct
- Phi-3.5-vision-instruct
- siglip2-base-patch16-256
- LightOnOCR-2-1B
- CLIP-ViT-H-14-laion2B-s32B-b79K
- InternVL2-2B
- GOT-OCR2_0
- gemma-4-31B
- chandra
- Qwen3-VL-235B-A22B-Instruct
- granite-docling-258M
- SmolVLM-256M-Instruct
- Qwen3-VL-30B-A3B-Instruct
- MinerU2.5-Pro-2605-1.2B
- dots.mocr
- granite-vision-3.3-2b
- UI-TARS-1.5-7B
- MiniCPM-V-4.6
- granite-vision-4.1-4b
- Llama-4-Scout-17B-16E-Instruct
- Phi-4-multimodal-instruct
- SmolVLM2-2.2B-Instruct
- SmolVLM-500M-Instruct
- Cosmos-Reason2-8B
- GLM-4.6V-Flash
- InternVL3-8B
- MiniCPM-V-4_5
- olmOCR-7B-0225-preview
- olmOCR-2-7B-1025
- Llama-3.1-Nemotron-Nano-VL-8B-V1
- gemma-4-12B
- Idefics3-8B-Llama3
- granite-4.0-3b-vision
- llava-onevision-qwen2-7b-ov-hf
- Llama-3.2-11B-Vision-Instruct
- Qianfan-OCR
- InternVL3_5-8B
- SmolVLM2-256M-Video-Instruct
- Emu3-Chat-hf
- GLM-4.5V
- SmolDocling-256M-preview
- Holo2-4B
- SmolVLM-Instruct
- Molmo-7B-D-0924
- NVIDIA-Nemotron-Nano-12B-v2-VL-BF16
- Step3-VL-10B
- Keye-VL-1_5-8B
- Llama-3.2-11B-Vision
- kosmos-2.5
- MinerU2.5-2509-1.2B
- NVLM-D-72B
- Molmo-72B-0924
- Llama-4-Maverick-17B-128E-Instruct
- Mage-VL
- deepseek-vl2
- LLaVA-OneVision-1.5-8B-Instruct
- Falcon-OCR
- Fara1.5-9B
- Fara-7B
- Phi-4-reasoning-vision-15B
- Llama-4-Scout-17B-16E
- Fara1.5-27B
- Llama-Guard-3-11B-Vision
- Youtu-VL-4B-Instruct
- Fara1.5-4B
- SmolVLM2-2.2B-Base
- MolmoMotion-4B-H1-F32
- Youtu-Parsing
- tipsv1-g14-lowres
- nemotron-labs-audio-visual-flamingo-hf
- Llama-3.2-90B-Vision-Instruct
- Keye-VL-2.0-30B-A3B
- tipsv1-l14
- tipsv1-g14
- tipsv1-so400m14
- Aquila-VL-2B-llava-qwen
- POINTS-Reader
- Llama-4-Maverick-17B-128E
- Perception-LM-8B
- cogvlm2-llama3-caption
- Video-XL-2
- tipsv1-s14
- Bunny-v1_1-Llama-3-8B-V
- tipsv1-b14
- Recon2Reason-Reasoning-4B
- Llama-3.2-90B-Vision
- LFM2-VL-1.6B
- LFM2.5-VL-1.6B
- ERNIE-4.5-VL-28B-A3B-PT
- diffusiongemma-26B-A4B-it
- North-Micro-Vision-Instruct
- Apriel-1.6-15b-Thinker
- surya-ocr-2
Hardware 120
Hardware configurations
All 120 configurations
- Lenovo ThinkStation P3 Tiny Gen 2 · RTX A1000 · 8 GB VRAM + 32 GB system RAM
- Lenovo Legion Pro 7i Gen 10 (16IAX10H) · RTX 5090 Laptop · 24 GB VRAM + 64 GB system RAM
- Lenovo LOQ 15IRX10 · RTX 5060 Laptop · 8 GB VRAM + 16 GB system RAM
- Lenovo ThinkPad T14 Gen 5 AMD · Ryzen 5 PRO 8540U · 16 GB system RAM
- Lenovo ThinkPad T14 Gen 5 AMD · Ryzen 7 PRO 8840U · 16 GB system RAM
- Lenovo ThinkPad T14 Gen 5 AMD · Ryzen 7 PRO 8840U · 32 GB system RAM
- Lenovo ThinkPad X1 Carbon Gen 14 Aura Edition · Core Ultra 7 355 · 32 GB system RAM
- Lenovo ThinkStation PGX · GB10 Grace Blackwell · 128 GB unified memory
- HP ZBook Fury 16 G11 · RTX 2000 Ada Laptop · 8 GB VRAM + 32 GB system RAM
- HP ZBook Fury 16 G11 · RTX 4000 Ada Laptop · 12 GB VRAM + 32 GB system RAM
- HP Z2 Mini G1a · Ryzen AI Max+ PRO 395 · 128 GB unified memory
- HP ZGX Nano G1n AI Station · GB10 Grace Blackwell · 128 GB unified memory
- Dell Alienware Area-51 (AAT2250) · RTX 5080 · 16 GB VRAM + 32 GB system RAM
- Dell Alienware Area-51 (AAT2250) · RTX 5090 · 32 GB VRAM + 32 GB system RAM
- Dell XPS 14 (2026, DA14260) · Core Ultra 7 358H · 32 GB system RAM
- Dell Alienware 16 Area-51 (AA16250) · RTX 5070 · 8 GB VRAM + 32 GB system RAM
- Dell Alienware 16X Aurora (AC16251) · RTX 5060 · 8 GB VRAM + 32 GB system RAM
- Dell Alienware 16X Aurora (AC16251) · RTX 5070 Ti · 12 GB VRAM + 32 GB system RAM
- Dell Precision 3591 · RTX 1000 Ada · 6 GB VRAM + 32 GB system RAM
- Dell Pro Max 16 Premium MA16250 · RTX PRO 2000 Blackwell · 8 GB VRAM + 32 GB system RAM
- Dell Pro Max with GB10 (FCM1253) · GB10 Grace Blackwell · 128 GB unified memory
- Apple Mac mini 2026 · M6 · 16 GB unified memory
- Apple Mac mini 2026 · M5 Pro · 24 GB unified memory
- Apple Mac mini 2026 · M6 · 24 GB unified memory
- Apple Mac mini 2026 · M6 · 32 GB unified memory
- Apple Mac mini 2026 · M5 Pro · 48 GB unified memory
- Apple Mac mini 2026 · M5 Pro · 64 GB unified memory
- Apple Mac mini 2024 · M4 · 16 GB unified memory
- Apple Mac mini 2024 · M4 · 24 GB unified memory
- Apple Mac mini 2024 · M4 Pro · 24 GB unified memory
- Apple Mac mini 2024 · M4 · 32 GB unified memory
- Apple Mac mini 2024 · M4 Pro · 48 GB unified memory
- Apple Mac mini 2023 · M2 · 8 GB unified memory
- Apple Mac mini 2023 · M2 · 16 GB unified memory
- Apple Mac mini 2023 · M2 · 24 GB unified memory
- Apple Mac mini 2020 · M1 · 8 GB unified memory
- Apple Mac mini 2020 · M1 · 16 GB unified memory
- Apple Mac Studio 2026 · M5 Max · 36 GB unified memory
- Apple Mac Studio 2026 · M5 Max · 48 GB unified memory
- Apple Mac Studio 2026 · M5 Max · 64 GB unified memory
- Apple Mac Studio 2026 · M5 Ultra · 96 GB unified memory
- Apple Mac Studio 2026 · M5 Max · 128 GB unified memory
- Apple Mac Studio 2026 · M5 Ultra · 256 GB unified memory
- Apple Mac Studio 2026 · M5 Ultra · 512 GB unified memory
- Apple iMac 24-inch 2024 · M4 · 16 GB unified memory
- Apple MacBook Neo 13-inch 2026 · A18 Pro · 8 GB unified memory
- Apple MacBook Air 13-inch 2026 · M5 · 16 GB unified memory
- Apple MacBook Air 13-inch 2026 · M5 · 24 GB unified memory
- Apple MacBook Air 13-inch 2026 · M5 · 32 GB unified memory
- Apple MacBook Air 15-inch 2026 · M5 · 16 GB unified memory
- Apple MacBook Air 15-inch 2026 · M5 · 32 GB unified memory
- Apple MacBook Air 13-inch 2025 · M4 · 16 GB unified memory
- Apple MacBook Air 13-inch 2025 · M4 · 24 GB unified memory
- Apple MacBook Air 13-inch 2025 · M4 · 32 GB unified memory
- Apple MacBook Pro 14-inch 2026 · M5 Pro · 24 GB unified memory
- Apple MacBook Pro 14-inch 2026 · M5 Max · 36 GB unified memory
- Apple MacBook Pro 14-inch 2026 · M5 Max · 48 GB unified memory
- Apple MacBook Pro 14-inch 2026 · M5 Pro · 48 GB unified memory
- Apple MacBook Pro 14-inch 2026 · M5 Max · 64 GB unified memory
- Apple MacBook Pro 14-inch 2026 · M5 Pro · 64 GB unified memory
- Apple MacBook Pro 14-inch 2026 · M5 Max · 128 GB unified memory
- Apple MacBook Pro 16-inch 2026 · M5 Pro · 24 GB unified memory
- Apple MacBook Pro 16-inch 2026 · M5 Max · 36 GB unified memory
- Apple MacBook Pro 16-inch 2026 · M5 Max · 48 GB unified memory
- Apple MacBook Pro 16-inch 2026 · M5 Pro · 64 GB unified memory
- Apple MacBook Pro 16-inch 2026 · M5 Max · 128 GB unified memory
- Apple MacBook Pro 14-inch (M5) 2025 · 16 GB unified memory
- Apple MacBook Pro 14-inch (M5) 2025 · 32 GB unified memory
- ASUS ROG NUC 2025 · RTX 5060 Laptop · 8 GB VRAM + 32 GB system RAM
- ASUS ROG NUC 2025 · RTX 5070 Laptop · 8 GB VRAM + 32 GB system RAM
- ASUS ROG NUC 2025 · RTX 5080 Laptop · 16 GB VRAM + 32 GB system RAM
- ASUS ROG Strix SCAR 18 (2026) · RTX 5090 Laptop · 24 GB VRAM + 32 GB system RAM
- ASUS ROG Flow Z13 (2025) · Ryzen AI MAX+ 395 · 128 GB unified memory
- ASUS ROG Zephyrus G14 (2025) · RTX 5070 Laptop · 8 GB VRAM + 16 GB system RAM
- ASUS ROG Zephyrus G14 (2025) · RTX 5070 Ti Laptop · 12 GB VRAM + 32 GB system RAM
- ASUS ROG Zephyrus G14 (2025) · RTX 5080 Laptop · 16 GB VRAM + 32 GB system RAM
- ASUS Ascent GX10 · GB10 Grace Blackwell · 128 GB unified memory
- Acer Veriton GN100 · GB10 Grace Blackwell · 128 GB unified memory
- Microsoft Surface Laptop 13.8-inch (8th Edition) · Snapdragon X2 Plus · 16 GB system RAM
- Microsoft Surface Laptop 13.8-inch (8th Edition) · Snapdragon X2 Elite · 64 GB system RAM
- Framework Desktop · Ryzen AI Max+ 395 · 64 GB unified memory
- Framework Desktop · Ryzen AI Max+ 395 · 128 GB unified memory
- NVIDIA RTX 5070 · 12 GB VRAM
- NVIDIA RTX 5060 · 8 GB VRAM
- NVIDIA RTX 5060 Ti · 8 GB VRAM
- NVIDIA RTX 5060 Ti · 16 GB VRAM
- NVIDIA RTX 5080 · 16 GB VRAM
- NVIDIA RTX 5070 Ti · 16 GB VRAM
- NVIDIA RTX 5090 · 32 GB VRAM
- NVIDIA RTX 4060 · 8 GB VRAM
- NVIDIA RTX 4060 Ti · 8 GB VRAM
- NVIDIA RTX 4060 Ti · 16 GB VRAM
- NVIDIA RTX 4070 · 12 GB VRAM
- NVIDIA RTX 4070 SUPER · 12 GB VRAM
- NVIDIA RTX 4070 Ti SUPER · 16 GB VRAM
- NVIDIA RTX 4090 · 24 GB VRAM
- NVIDIA RTX 4080 SUPER · 16 GB VRAM
- NVIDIA RTX 3060 · 12 GB VRAM
- NVIDIA RTX 3050 · 6 GB VRAM
- NVIDIA RTX 3050 · 8 GB VRAM
- NVIDIA RTX 3060 Ti · 8 GB VRAM
- NVIDIA RTX 3070 · 8 GB VRAM
- NVIDIA RTX 3090 · 24 GB VRAM
- NVIDIA GTX 1650 · 4 GB VRAM
- NVIDIA RTX 4060 Laptop GPU · 8 GB VRAM
- NVIDIA RTX 5060 Laptop GPU · 8 GB VRAM
- NVIDIA RTX 3060 Laptop GPU · 6 GB VRAM
- NVIDIA RTX 4050 Laptop GPU · 6 GB VRAM
- NVIDIA RTX 4070 Laptop GPU · 8 GB VRAM
- NVIDIA RTX 5070 Laptop GPU · 8 GB VRAM
- NVIDIA RTX 5070 Laptop GPU · 12 GB VRAM
- NVIDIA RTX 5080 Laptop GPU · 16 GB VRAM
- NVIDIA RTX 5090 Laptop GPU · 24 GB VRAM
- NVIDIA DGX H100 · 640 GB VRAM across 8 GPUs
- NVIDIA DGX Spark · 128 GB unified memory
- AMD Radeon RX 9070 XT · 16 GB VRAM
- AMD Radeon RX 9060 XT · 8 GB VRAM
- AMD Radeon RX 9060 XT · 16 GB VRAM
- AMD Radeon RX 7800 XT · 16 GB VRAM
- AMD Radeon RX 7900 XTX · 24 GB VRAM
Model families 13
Sizes of one release line, side by side
Comparisons 32
Task and hardware comparisons
All 32 comparisons
- Qwen 9B vs 27B for local text
- Qwen 27B vs 35B A3B for coding
- FLUX.2 dev vs Qwen-Image workflows
- Qwen3 8B vs Llama 3.1 8B for local chat
- gpt-oss-20b vs Qwen3 30B A3B for local chat
- Phi-4 vs Mistral Small 3.2 for local text
- Qwen3 Coder 30B vs Devstral Small 2 for coding
- Ministral 3 8B vs Llama 3.1 8B for local text
- Granite 4.2 8B vs Qwen3 8B for business use
- Gemma 4 26B A4B vs Qwen3 30B A3B for local chat
- Gemma 4 31B vs Qwen3.8 27B for local text
- Stable Diffusion 3.5 Large vs FLUX.1 dev for images
- HunyuanImage 3.0 vs Qwen-Image 2512 for images
- FLUX.2 klein 4B vs Z-Image Turbo for fast images
- Gemma 4 26B A4B vs Qwen3-VL 30B A3B for images
- Molmo 7B vs MiniCPM-V 4.5 for images
- Wan 2.2 vs HunyuanVideo for local video
- Whisper large-v3 vs large-v3-turbo for transcription
- BGE-M3 vs Qwen3-Embedding 0.6B for local search
- EmbeddingGemma vs multilingual-e5-large for embeddings
- ASUS Ascent GX10 vs Dell Pro Max GB10
- NVIDIA DGX Spark vs ASUS Ascent GX10
- NVIDIA DGX Spark vs Framework Desktop 128 GB
- NVIDIA DGX Spark vs Mac Studio M5 Max 128 GB
- Mac Studio M5 Max 128 GB vs Framework Desktop 128 GB
- Mac mini M4 16 GB vs RTX 4060 8 GB
- RTX 4060 Ti 16 GB vs RTX 4070 12 GB
- RTX 5060 Ti 16 GB vs RTX 4060 Ti 16 GB
- RTX 5070 Ti vs RTX 4080 SUPER
- RTX 3090 vs RTX 4090
- RTX 4090 vs RTX 5090
- RTX 4090 vs Radeon RX 7900 XTX
Catalog profiles 38
Hub checkpoints with publisher evidence and a hardware answer
All 38 catalog profiles
- bigstral-12b-32k
- Dracarys-Llama-3.1-70B-Instruct
- Dracarys2-72B-Instruct
- Dracarys2-Llama-3.1-70B-Instruct
- Smaug-Llama-3-70B-Instruct
- Smaug-Llama-3-70B-Instruct-32K
- Smaug-Qwen2-72B-Instruct
- BAR-7B
- Molmo2-8B
- gemma-3n-E4B-it
- medgemma-4b-it
- SmolLM2-1.7B
- SmolLM2-1.7B-Instruct
- SmolLM2-135M
- SmolLM2-135M-Instruct
- SmolLM2-360M
- SmolLM2-360M-Instruct
- granite-3.1-1b-a400m-instruct
- granite-3b-code-base-128k
- granite-3b-code-instruct-128k
- granite-8b-code-base-128k
- granite-8b-code-instruct-128k
- granite-guardian-4.1-8b
- Llama-3.1-405B
- Llama-3.1-405B-Instruct
- Llama-3.1-70B
- Llama-3.1-70B-Instruct
- Llama-3.1-8B
- Llama-Guard-4-12B
- Florence-2-base
- Florence-2-large
- Eagle2.5-8B
- MiniCPM-V-2_6
- Qwen3-235B-A22B-Instruct-2507
- Qwen3-235B-A22B-Thinking-2507
- Qwen3-30B-A3B-Thinking-2507
- Qwen3-4B-Thinking-2507
- step3