Skip to content
Local AI Wizard
Your machine
Theme

Dell Alienware Area-51 (AAT2250) · Core Ultra 9 285K · RTX 5090 32 GB · 32 GB

Dell · Dell Alienware Area-51 (AAT2250)

767 text models run well · 1,792 GB/s bandwidth

Models on this hardware

Start here

Text

Within 32 GB: 767 run well · 2 tight · 37 reviewed · 57 more run slowly

Text · LiveBench · overall

0–100 · higher is better

  • Color = publisher

Source: LiveBench 2026-06-25 · collected 2026-10-18 · Open models without a score are not drawn (no score ≠ 0).

Rows run well first, then tight fits; within each, reviewed models, then Hub downloads over 30 days, not quality. Sort a score column to rank by that source alone.
Text models that run well within 32 GB
Smaug MiniAbacus AI · 27BQ4 · published params · source76.9Not on the LMArena text leaderboard of 2026-10-22~23 GBQ4 · published paramssource
Qwen3.8 27BAlibaba · 27B · LMArena 1,437Q4 · published params · source75.31,437 ± 5~23 GBQ4 · published paramssource
Qwen3.6 27BAlibaba · 27BQ4 · published params · source64.0Not on the LMArena text leaderboard of 2026-10-22~23 GBQ4 · published paramssource
Nemotron 3.5 Lightning 30B A3BNVIDIA · 30BQ4 · published params · source44.5Arena rated the NVFP4 build, NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4); this entry is the BF16 reference, which NVIDIA reports with different scores~25 GBQ4 · published paramssource
Qwen3 14BAlibaba · 14.8BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~14 GBQ4 · published paramssource
Qwen3.5 9BAlibaba · 9BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~9 GBQ4 · published paramssource
Gemma 4 31BGoogle · 30.7B · LMArena 1,452Q4 · published params · sourceNo comparable published result1,452 ± 7~26 GBQ4 · published paramssource
Qwen3 8BAlibaba · 8.2BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~9 GBQ4 · published paramssource
8 of 769

LMArena ratings in this table: LMArena 2026-10-22 · collected 2026-10-25 · dataset · CC BY 4.0

Tight fit: it runs, but leaves less than 3.2 GB free beyond the 2 GB the system keeps (the memory figure already includes that reserve).

Every reviewed text model here 37

Every one that runs here, well or slowly, scored or not; 20 of 37 have a LiveBench or LMArena result. Run well first, then tight fits, then slow; within each, by Hub downloads over 30 days, read 2026-11-19, not by quality.

Reviewed text models that run on Dell Alienware Area-51 (AAT2250) · Core Ultra 9 285K · RTX 5090 32 GB · 32 GB
Qwen3 14BAlibaba · 14.8BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~14 GB9.0Apache 2.013.2M
Qwen3.8 27BAlibaba · 27B75.31,437~23 GB16.5Apache 2.06.9M
Qwen3.5 9BAlibaba · 9BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~9 GB5.7Apache 2.06.5M
Gemma 4 31BGoogle · 30.7BNot in LiveBench 2026-06-251,452~26 GB18.3Apache 2.06.3M
Qwen3 8BAlibaba · 8.2BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~9 GB5.0Apache 2.06.1M
gpt-oss-20bOpenAI · 21BNot in LiveBench 2026-06-251,317~18 GB11.6Apache 2.05.6M
Gemma 4 26B A4BGoogle · 25.2BNot in LiveBench 2026-06-251,437~21 GB16.9Apache 2.05M
Gemma 4 E4BGoogle · 8BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~8 GB5.0Apache 2.04.4M
8 of 37
Also runs slowly57 models

Above the 32 GB of VRAM, the layers that do not fit run on the CPU from PC RAM, up to 56 GB in all (listed RAM: 32 GB). Planning estimate, not a speed figure.

6 of 57

Browse Text models

Adjust the estimate: quantization, context, reserveloads the live catalog

Vision

Within 32 GB: 1,028 run well · 31 tight · 10 reviewed · 5 more run slowly

Vision · LMArena

rating · higher is better

  • Color = publisher

Source: LMArena 2026-10-19 · collected 2026-10-25 · dataset · CC BY 4.0 · Models without a rating are left out, not scored as zero.

Rows run well first, then tight fits; within each, reviewed models, then Hub downloads over 30 days, not quality. Sort a score column to rank by that source alone.
Vision models that run well within 32 GB
Gemma 4 31BGoogle · 30.7B · Image to text · LMArena 1,262Q4 · published params · source1,262 ± 6~26 GBQ4 · published paramssource
Qwen3.8 27BAlibaba · 27B · Image to text · LMArena 1,242Q4 · published params · source1,242 ± 8~23 GBQ4 · published paramssource
Gemma 4 26B A4BGoogle · 25.2B · Image to text · LMArena 1,242Q4 · published params · source1,242 ± 6~21 GBQ4 · published paramssource
gemma-3-27b-itgoogle · 27.43B · Image to text · LMArena 1,160Q4 · Hugging Face count · source1,160 ± 8~23 GBQ4 · Hugging Face countsource
Qwen2.5-VL-32B-InstructQwen · 33.45B · Image to text · LMArena 1,119Q4 · Hugging Face count · source1,119 ± 15~28 GBQ4 · Hugging Face countsource
Molmo2-8Ballenai · 8.66B · Image to text · LMArena 1,112Q4 · Hugging Face count · source1,112 ± 20~9 GBQ4 · Hugging Face countsource
Qwen2-VL-7B-InstructQwen · 8.29B · Image to text · LMArena 1,031Q4 · Hugging Face count · source1,031 ± 11~9 GBQ4 · Hugging Face countsource
Molmo-7B-D-0924allenai · 8.02B · Image to text · LMArena 994Q4 · Hugging Face count · source994 ± 14~9 GBQ4 · Hugging Face countsource
8 of 1,059

LMArena ratings in this table: LMArena 2026-10-19 · collected 2026-10-25 · dataset · CC BY 4.0

Tight fit: it runs, but leaves less than 3.2 GB free beyond the 2 GB the system keeps (the memory figure already includes that reserve).

Also runs slowly5 models

Above the 32 GB of VRAM, the layers that do not fit run on the CPU from PC RAM, up to 56 GB in all (listed RAM: 32 GB). Planning estimate, not a speed figure.

471 more vision models in the catalog have no usable memory figure or parameter count for this profile. Browse Vision models

Image

151 within 32 GB

Image · Prompt alignment · GenEval

0–1 · higher is better

Source: GenEval · 2023 · reviewed 2026-10-05 · Published quality in the original benchmark preset; not measured on this hardware.

Image models within 32 GB
Stable Diffusion XL 1.0Stability AI · 2.6B · Text to imagePlatform path documented · stable-diffusion.cpp · source0.55Not on the LMArena text-to-image leaderboard of 2026-10-07Documented path without a memory figurePlatform path documentedstable-diffusion.cpp · source
Stable Diffusion 1.5Stability AI · 0.98B · Text to imagePlatform path documented · stable-diffusion.cpp · source0.43Not on the LMArena text-to-image leaderboard of 2026-10-07Documented path without a memory figurePlatform path documentedstable-diffusion.cpp · source
BagelByteDance · 14B · Text to image · LMArena 898Publisher minimum · CUDA · sourceNo comparable published result898 ± 6~32 GBPublisher minimumCUDA · source
Qwen-Image-NVFP4nvidia · 12.1B · Text to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~32 GB16-bit est. · paramssource
Step1X-Edit-v1p1-diffusersstepfun-ai · 12.4B · Image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~32 GB16-bit est. · paramssource
Step1X-Edit-v1p2stepfun-ai · 12.4B · Image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~32 GB16-bit est. · paramssource
Step1X-Edit-v1p2-previewstepfun-ai · 12.4B · Image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~32 GB16-bit est. · paramssource
FLUX.1 Krea [dev]Black Forest Labs · 12B · Text to image16-bit est. · params · sourceNo comparable published resultNot on the LMArena text-to-image leaderboard of 2026-10-07~31 GB16-bit est. · paramssource
8 of 151

LMArena ratings in this table: LMArena 2026-10-07 · collected 2026-10-25 · dataset · CC BY 4.0

231 more image models in the catalog have no usable memory figure or parameter count for this profile. Browse Image models

Video

65 within 32 GB
Video models within 32 GB
LTX-2.5 FastLightricks · 22B · Text to videoPublisher minimum · CUDA · source~32 GBPublisher minimumCUDA · source
LTX-2.5 ProLightricks · 22B · Text to videoPublisher minimum · CUDA · source~32 GBPublisher minimumCUDA · source
Open-Sora-v2hpcai-tech · 11B · Text to video16-bit est. · params · source~29 GB16-bit est. · paramssource
Video-As-Prompt-CogVideoX-5BByteDance · 11.1B · Image to video16-bit est. · params · source~29 GB16-bit est. · paramssource
mochi-1-previewgenmo · 10B · Text to video16-bit est. · params · source~26 GB16-bit est. · paramssource
Wan2.2-TI2V-5BWan-AI · 5B · Text to videoConditional path · CUDA · source~24 GBConditional pathCUDA · source
Wan2.2-TI2V-5B-DiffusersWan-AI · 5B · Text to videoConditional path · CUDA · source~24 GBConditional pathCUDA · source
ContentV-8BByteDance · 8.1B · Text to video16-bit est. · params · source~22 GB16-bit est. · paramssource
8 of 65

How this list works Documented execution paths on this hardware first, then publisher minimums (CUDA or Apple MPS).

124 more video models in the catalog have no usable memory figure or parameter count for this profile. Browse Video models

Audio

382 within 32 GB

Audio · Word error rate · Open ASR

% · lower is better

Source: Word error rate · Open ASR · reviewed 2026-10-20 · Published quality in the original benchmark preset; not measured on this hardware.

Audio models within 32 GB
Whisper large-v3-turboOpenAI · 0.81B · Speech to textPlatform path documented · whisper.cpp / CUDA · source7.83Documented path without a memory figurePlatform path documentedwhisper.cpp / CUDA · source
Whisper large-v3OpenAI · 1.55B · Speech to textPlatform path documented · whisper.cpp / CUDA · source7.44Documented path without a memory figurePlatform path documentedwhisper.cpp / CUDA · source
acestep-captionerACE-Step · 10.7B · Sound effects and audio16-bit est. · params · sourceNo comparable published result~28 GB16-bit est. · paramssource
acestep-transcriberACE-Step · 10.7B · Speech to text16-bit est. · params · sourceNo comparable published result~28 GB16-bit est. · paramssource
MERaLiON-2-10BMERaLiON · 10.1B · Speech to text16-bit est. · params · sourceNo comparable published result~27 GB16-bit est. · paramssource
MERaLiON-2-10B-ASRMERaLiON · 10.1B · Speech to text16-bit est. · params · sourceNo comparable published result~27 GB16-bit est. · paramssource
Kimi-Audio-7Bmoonshotai · 9.8B · Text to speech16-bit est. · params · sourceNo comparable published result~26 GB16-bit est. · paramssource
Kimi-Audio-7B-Instructmoonshotai · 9.8B · Text to speech16-bit est. · params · sourceNo comparable published result~26 GB16-bit est. · paramssource
8 of 382

1,984 more audio models in the catalog have no usable memory figure or parameter count for this profile. Browse Audio models

Embeddings

650 run well within 32 GB

Embeddings · MTEB (Multilingual, v2) · mean(task)

0–100 · higher is better

  • Color = publisher

Source: MTEB results (curated rows, sourced per model)

Embeddings models that run well within 32 GB
Qwen3-Embedding 8BAlibaba (Qwen)8-bit · published params · source70.6~12 GB8-bit · published paramssource
Qwen3-Embedding 4BAlibaba (Qwen)8-bit · published params · source69.5~7 GB8-bit · published paramssource
Harrier OSS v1 (0.6B)Microsoft8-bit · published params · source69.0~3 GB8-bit · published paramssource
Qwen3-Embedding 0.6BAlibaba (Qwen)8-bit · published params · source64.3~3 GB8-bit · published paramssource
Multilingual E5 Large Instructintfloat8-bit · published params · source63.2~3 GB8-bit · published paramssource
EmbeddingGemma 2Google8-bit · published params · source61.4~3 GB8-bit · published paramssource
EmbeddingGemma (300M)Google8-bit · published params · source61.1~3 GB8-bit · published paramssource
BGE-M3BAAI8-bit · published params · source59.6~3 GB8-bit · published paramssource
8 of 650

Browse Embeddings models

Runs well within 32 GB of VRAM · planning estimates, not measured speed live catalog · 19,444 repositories · checked

Measurements

Published tokens per second, exactly as measured; never estimated.

Published measurements on this hardware
gpt-oss 20B Q4_K_Munsloth/gpt-oss-20b-GGUF/gpt-oss-20b-Q4_K_M…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)393.3 ± 2.62Q4_K_M
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
gpt-oss 20B Q8_0unsloth/gpt-oss-20b-GGUF/gpt-oss-20b-Q8_0.g…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)374.72 ± 2.73Q8_0
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
Qwen3-Coder 30B-A3B Q4_K_Munsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF/Q…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)346.27 ± 3.49Q4_K_M
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
Llama 2 7B Q4_0Llama 2 7B Q4_0 (scoreboard model; the scor…NVIDIA GeForce RTX 5090 · 32 GB GDDR7 (the scoreboard names the GPU, not the machine or its power limit)300.40 ± 0.28Q4_0
0 / 128 · Single llama-bench process;…
CUDA
llama.cpp commit 8cf6b42
Flash Attention enabled
llama.cpp CUDA scoreboard · community result
2026-10-25
gpt-oss-20b MXFP4gpt-oss-20b-mxfp4.gguf (ggml-org/gpt-oss-20…NVIDIA GeForce RTX 5090 · 32 GB (the guide names the GPU, not the machine or its power limit)282.51 ± 0.44MXFP4 (native gpt-oss weights)
0 / 128 · Single llama-bench process;…
llama.cpp CUDA
llama.cpp commit a094f381 (6210)
Flash Attention enabled
llama.cpp gpt-oss guide · maintainer result
2026-10-25
Llama 2 7B Q4_0Llama 2 7B Q4_0 (scoreboard model; the scor…Nvidia RTX 5090 · 32 GB (memory size not stated by the source; this chip is sold with one memory size) · coopmat2273.68 ± 0.52Q4_0
0 / 128 · Single llama-bench process;…
Vulkan
llama.cpp commit ca71fb9
Flash Attention enabled
llama.cpp Vulkan scoreboard · community result
2026-10-25
Gemma 4 26B-A4B UD-Q4_K_Munsloth/gemma-4-26B-A4B-it-GGUF/gemma-4-26B…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)231.41 ± 1.95UD-Q4_K_M
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
Qwen3.5 9B Q4_K_Munsloth/Qwen3.5-9B-GGUF/Qwen3.5-9B-Q4_K_M.g…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)220.46 ± 1.18Q4_K_M
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
Gemma 4 26B-A4B Q8_0unsloth/gemma-4-26B-A4B-it-GGUF/gemma-4-26B…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)217.48 ± 1.82Q8_0
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
Qwen3.5 9B Q8_0unsloth/Qwen3.5-9B-GGUF/Qwen3.5-9B-Q8_0.ggufNVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)156.01 ± 0.80Q8_0
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
Gemma 4 12B Q4_K_Munsloth/gemma-4-12b-it-GGUF/gemma-4-12b-it-…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)152.43 ± 0.68Q4_K_M
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
Gemma 4 12B Q8_0unsloth/gemma-4-12b-it-GGUF/gemma-4-12b-it-…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)103.67 ± 0.38Q8_0
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
Mistral Small 3.2 24B Q4_K_Munsloth/Mistral-Small-3.2-24B-Instruct-2506…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)101.14 ± 0.24Q4_K_M
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
Qwen3.6 27B Q4_K_Munsloth/Qwen3.6-27B-GGUF/Qwen3.6-27B-Q4_K_M…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)77.61 ± 0.38Q4_K_M
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
Gemma 4 31B Q4_K_Munsloth/gemma-4-31B-it-GGUF/gemma-4-31B-it-…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)71.3 ± 0.23Q4_K_M
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
Mistral Small 3.2 24B Q8_0unsloth/Mistral-Small-3.2-24B-Instruct-2506…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)63.85 ± 0.10Q8_0
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25
Qwen3.6 27B Q8_0unsloth/Qwen3.6-27B-GGUF/Qwen3.6-27B-Q8_0.g…NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host) (the dataset names the GPU, not the machine or its power limit)52.36 ± 0.22Q8_0
0 / 128 · Single llama-bench process
llama.cpp CUDA
llama.cpp commit 3e4dfa8f3 (b11658)
Flash Attention enabled
Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0
2026-10-25

Specifications

17 sourced fields; the source is named once per group, and a field from another source links to it. Official specifications

GPU VRAM32 GBDedicated · what models load into · source
System RAM32 GBInstalled · not added to VRAM · source
Memory bandwidth1,792 GB/sManufacturer spec · not model speed · source
Where to buyDell.comManufacturer link · choose the configuration there · US · recorded

Marker: the best LiveBench-scored text model that runs well here. No other text model would run well with the next memory size. Q4 planning estimate, not a measured fit.

Reviewed · Manufacturer source

CPU cores
24
Processor
Intel Core Ultra 9 285K
Graphics processor
NVIDIA GeForce RTX 5090
GPU runtime status
Not stated by the source
Memory capacity
32 GB
Memory kind
System RAM
CUDA cores
21,760
Dimensions (mm)
610.50 (L) × 231.60 (W) × 569.00 (H)
GPU VRAM
32 GB
GPU power
575 W
Installed storage
2,000 GB
Memory interface
512 bit
Operating system
Windows 11 Home
Power supply
1,500 W
Installed memory configuration
(2 × 16 GB) DDR5 XMP up to 6400 MT/s
Weight
34.5 kg

Family specification

Checked · Manufacturer source

NPU performance
13 TOPS · INT8

Intel Core Ultra 9 285K · NVIDIA GeForce RTX 5090 with 32 GB installed system RAM and 32 GB dedicated GPU VRAM. Runtime support and local inference speed are not verified.

Photo: Dell family photo · memory configuration is not pictured. · Manufacturer source

Memory bandwidth is not measured model speed; verify runtime and checkpoint compatibility. Hardware specification reviewed: 2026-10-18.

How estimates work
Candidates
Reviewed pages use published parameter counts; automatic text candidates use official repository tensor counts (packed quantized weights and unsupported architectures excluded).
Planning
Q4 weights + 20% allowance + reserve: 25% of unified or system memory (at least 2 GB, at most 8 GB; 2 GB here) or 2 GB per dedicated GPU. Adjustable in “Adjust the estimate”. No KV cache is calculated from context.
Fit tiers
Runs well: the estimate fits the fast memory (VRAM, or unified memory within the macOS GPU share). Runs slowly: within the machine's memory but outside the fast part; a graphics card offloads layers to PC RAM (the listed RAM, or 32 GB assumed). Doesn't run: above both. Tiers are planning estimates, never a speed.
Vision
Vision-language models use the Q4 planning estimate from the parameter count (published by the model page, or read from Hugging Face). Classic vision models (classify, detect, segment) use a 16-bit estimate. No vision benchmark is tracked, so rows carry no score.
Media and embeddings
Media rows use documented execution paths (exact hardware or platform) and publisher minimums; a published requirement above this memory moves a model to the next tier. Without either, a 16-bit estimate from the published parameter count (× 1.2 + 2 GB), labelled as such. Embeddings use 8-bit weights + 20% + 2 GB.

Local AI basics: parameters, Q4 and memory · Full model catalog · Data and methodology

Alternatives

Other machines on the same memory ladder (VRAM); each page lists the models that fit it.