Skip to content
Local AI Wizard
Your machine
Theme

Models on this hardware

Start here

Text

Within 200 GB: 194 run well · 2 tight · 39 reviewed · 4 more run slowly (4 of them run well with 512 GB) · 4 more with 512 GB

Text · LiveBench · overall

0–100 · higher is better

  • Color = publisher

Source: LiveBench 2026-06-25 · collected 2026-09-26 · 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 200 GB
Smaug MiniAbacus AI · 27BQ4 · published params · source76.9Not on the LMArena text leaderboard of 2026-10-22~29 GBQ4 · published paramssource
Qwen3.8 27BAlibaba · 27B · LMArena 1,437Q4 · published params · source75.31,437 ± 5~29 GBQ4 · published paramssource
Qwen3.6 27BAlibaba · 27BQ4 · published params · source64.0Not on the LMArena text leaderboard of 2026-10-22~29 GBQ4 · published paramssource
Qwen3 14BAlibaba · 14.8BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~20 GBQ4 · published paramssource
Gemma 4 31BGoogle · 30.7B · LMArena 1,452Q4 · published params · sourceNo comparable published result1,452 ± 7~32 GBQ4 · published paramssource
Gemma 4 26B A4BGoogle · 25.2B · LMArena 1,437Q4 · published params · sourceNo comparable published result1,437 ± 7~27 GBQ4 · published paramssource
Qwen3 8BAlibaba · 8.2BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~15 GBQ4 · published paramssource
Qwen3.5 9BAlibaba · 9BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~15 GBQ4 · published paramssource
8 of 196

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 20 GB free beyond the 8 GB the system keeps (the memory figure already includes that reserve).

Every reviewed text model here 43

Every one that runs here, well or slowly, scored or not (39 run well, 4 slowly); 23 of 43 have a LiveBench or LMArena result. Run well first, then tight fits, then slow; within each, by Hub downloads over 30 days, read 2026-10-25, not by quality.

Reviewed text models that run on Mac Studio M5 Ultra · 256 GB unified
Qwen3 14BAlibaba · 14.8BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~20 GB9.0Apache 2.010.4M
Gemma 4 31BGoogle · 30.7BNot in LiveBench 2026-06-251,452~32 GB18.3Apache 2.08.4M
Gemma 4 26B A4BGoogle · 25.2BNot in LiveBench 2026-06-251,437~27 GB16.9Apache 2.08.2M
Qwen3 8BAlibaba · 8.2BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~15 GB5.0Apache 2.08.1M
Qwen3.8 27BAlibaba · 27B75.31,437~29 GB16.5Apache 2.07.8M
Qwen3.5 9BAlibaba · 9BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~15 GB5.7Apache 2.06.1M
gpt-oss-20bOpenAI · 21BNot in LiveBench 2026-06-251,317~24 GB11.6Apache 2.05.8M
Llama 3.1 8B InstructMeta · 8BNot in LiveBench 2026-06-251,211~14 GB4.9Llama 3.14.8M
8 of 43

With 512 GB you also run… 4

The next memory size on this ladder runs these well. Figures are the requirement on this hardware type.

Browse Text models

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

Vision

Within 200 GB: 150 run well · 2 tight · 10 reviewed · 2 more run slowly (2 of them run well with 512 GB) · 3 more with 512 GB

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 200 GB
Gemma 4 31BGoogle · 30.7B · Image to text · LMArena 1,262Q4 · published params · source1,262 ± 6~32 GBQ4 · published paramssource
Qwen3.8 27BAlibaba · 27B · Image to text · LMArena 1,242Q4 · published params · source1,242 ± 8~29 GBQ4 · published paramssource
Gemma 4 26B A4BGoogle · 25.2B · Image to text · LMArena 1,242Q4 · published params · source1,242 ± 6~27 GBQ4 · published paramssource
Qwen3-VL-235B-A22B-InstructQwen · 235.67B · Image to text · LMArena 1,215Q4 · Hugging Face count · source1,215 ± 7~185 GBTight fit: Needs ~185 GB: runs well, about 15 GB left beyond the system reserveQ4 · Hugging Face countsource
gemma-3-27b-itgoogle · 27.43B · Image to text · LMArena 1,160Q4 · Hugging Face count · source1,160 ± 8~29 GBQ4 · Hugging Face countsource
GLM-4.5Vzai-org · 107.71B · Image to text · LMArena 1,153Q4 · Hugging Face count · source1,153 ± 12~89 GBQ4 · Hugging Face countsource
Llama-4-Scout-17B-16E-Instructmeta-llama · 108.6B · Image to text · LMArena 1,128Q4 · Hugging Face count · source1,128 ± 10~90 GBQ4 · Hugging Face countsource
Qwen2.5-VL-32B-InstructQwen · 33.45B · Image to text · LMArena 1,119Q4 · Hugging Face count · source1,119 ± 15~34 GBQ4 · Hugging Face countsource
8 of 152

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 20 GB free beyond the 8 GB the system keeps (the memory figure already includes that reserve).

Also runs slowly2 models

Above the macOS default GPU share (200 GB here, reserve included) but within the 256 GB installed: the rest runs on the CPU unless the limit is raised. Planning estimate, not a speed figure.

  • GLM-5.3 FlashZ.ai~248 GBruns well with 512 GB
  • step3stepfun-ai~249 GBruns well with 512 GB

With 512 GB you also run… 3

The next memory size on this ladder runs these well. Figures are the requirement on this hardware type.

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

Image

82 within 200 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 200 GB
Stable Diffusion XL 1.0Stability AI · 2.6B · Text to imagePlatform path documented · Apple Core ML · source0.55Not on the LMArena text-to-image leaderboard of 2026-10-07Documented path without a memory figurePlatform path documentedApple Core ML · source
Stable Diffusion 1.5Stability AI · 0.98B · Text to imagePlatform path documented · Apple Core ML · source0.43Not on the LMArena text-to-image leaderboard of 2026-10-07Documented path without a memory figurePlatform path documentedApple Core ML · source
HunyuanImage 3.0 (Fal)Tencent · 80B · Text to image · LMArena 1,15016-bit est. · params · sourceNo comparable published result1,150 ± 3~194 GB16-bit est. · paramssource
HunyuanImage 3.0 Instruct (Fal)Tencent · 80B · Text to image16-bit est. · params · sourceNo comparable published resultArena rated hunyuan-image-3.0; this entry is the Instruct checkpoint~194 GB16-bit est. · paramssource
Cosmos3-Super-Text2ImageNVIDIA · 64B · Text to image · LMArena 1,15216-bit est. · params · sourceNo comparable published result1,152 ± 6~156 GB16-bit est. · paramssource
Cosmos3-Super-Text2Image (agentic)NVIDIA · 64B · Text to image · LMArena 1,16516-bit est. · params · sourceNo comparable published result1,165 ± 7~156 GB16-bit est. · paramssource
Cosmos3-Super-Text2Image-4StepNVIDIA · 64B · Text to image16-bit est. · params · sourceNo comparable published resultArena rated Cosmos3-Super-Text2Image; this entry is the 4-step distilled checkpoint~156 GB16-bit est. · paramssource
Emu3.5-ImageBAAI · 34.1B · Text + image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~84 GB16-bit est. · paramssource
8 of 82

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

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

Video

74 within 200 GB
Video models within 200 GB
Cosmos3-Super-Image2Videonvidia · 64.6B · Image to video16-bit est. · params · source~158 GB16-bit est. · paramssource
Cosmos3-Super-Image2Video-4Stepnvidia · 64B · Image to video16-bit est. · params · source~156 GB16-bit est. · paramssource
MiniMax H3MiniMax · 33B · Text to video16-bit est. · params · source~82 GB16-bit est. · paramssource
Kandinsky-6.0-Pro-distill-5s-Diffuserskandinskylab · 30.1B · Image to video16-bit est. · params · source~75 GB16-bit est. · paramssource
stepvideo-t2vstepfun-ai · 29.3B · Text to video16-bit est. · params · source~73 GB16-bit est. · paramssource
stepvideo-ti2vstepfun-ai · 29.4B · Image to video16-bit est. · params · source~73 GB16-bit est. · paramssource
Wan2.2 T2V-A14BWan-AI · 27B · Text to video16-bit est. · params · source~67 GB16-bit est. · paramssource
Wan2.2-I2V-A14BWan-AI · 27B · Image to video16-bit est. · params · source~67 GB16-bit est. · paramssource
8 of 74

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

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

Audio

132 within 200 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 200 GB
Whisper large-v3-turboOpenAI · 0.81B · Speech to textPlatform path documented · whisper.cpp / Metal · source7.83Documented path without a memory figurePlatform path documentedwhisper.cpp / Metal · source
Whisper large-v3OpenAI · 1.55B · Speech to textPlatform path documented · whisper.cpp / Metal · source7.44Documented path without a memory figurePlatform path documentedwhisper.cpp / Metal · source
Step-Audio-R1.1stepfun-ai · 33.5B · Speech to text16-bit est. · params · sourceNo comparable published result~83 GB16-bit est. · paramssource
Voxtral-Small-24B-2507mistralai · 24.3B · Speech to text16-bit est. · params · sourceNo comparable published result~61 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
Llasa-8BHKUSTAudio · 8.6B · Text to speech16-bit est. · params · sourceNo comparable published result~23 GB16-bit est. · paramssource
MOSS-TTS-v1.5OpenMOSS-Team · 8.5B · Text to speech16-bit est. · params · sourceNo comparable published result~23 GB16-bit est. · paramssource
8 of 132

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

Embeddings

91 run well within 200 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 200 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 91

Browse Embeddings models

Runs well within 200 GB of unified memory · planning estimates, not measured speed bundled catalog copy · 1,777 repositories · checked

Measurements

Speed on this hardware

no published measurement yetWe have not yet included a verifiable measurement for this exact configuration. The memory estimates above do not indicate tokens per second or time to first token.

Specifications

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

Unified memory256 GBShared by CPU and GPU · source
Memory bandwidth1,200 GB/sManufacturer spec · not model speed · source
Where to buyApple StoreManufacturer link · choose the configuration there · US · recorded

Markers: the best LiveBench-scored text model that runs well here, and the lightest text model that does not run well here but runs well with 512 GB. Q4 planning estimates, not measured fits.

Selected configuration

Latest check · Manufacturer source

Memory capacity
256 GB
Memory type
256 GB unified
Chip / processor
Apple M5 Ultra · 36 CPU / 80 GPU cores
Memory bandwidth (manufacturer limit)
1,200 GB/s
CPU
Apple M5 Ultra
CPU cores
36
GPU
Apple M5 Ultra GPU
GPU cores
80

Family specification

Latest check · Manufacturer source

Ports (M5 Ultra family)
6 × Thunderbolt 5 · 2 × USB-A (5 Gb/s) · SDXC (UHS-II) · HDMI 2.1 · 10Gb Ethernet · 3.5 mm
Maximum continuous power (specification)
480 W
Release date
2026-09-22
Weight
3.6 kg
Introduced
2026
Wi-Fi
Wi-Fi 7 (802.11be)
Bluetooth
Bluetooth 6
Dimensions (cm)
19.7 × 19.7 × 9.5 (W × D × H)
Operating system
macOS
Maximum Thunderbolt rate
120 Gb/s
Storage options (family)
Base storage: 1 TB; configure-to-order options: 2 TB, 4 TB, 8 TB or 16 TB.
Neural Engine cores
32

A 256 GB unified-memory configuration, not the maximum available configuration. Reserve memory for the OS, KV cache and multimodal components; verify a Metal/MLX path.

Photo: Official manufacturer image. · Manufacturer source

Memory bandwidth is not measured model speed; verify runtime and checkpoint compatibility. Hardware specification reviewed: 2026-10-13.

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; 8 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 (unified memory); each page lists the models that fit it.