Skip to content
Local AI Wizard
Your machine
Theme

Models on this hardware

Start here

Text

Within 80 GB: 191 run well · 37 reviewed · 2 more with 128 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. No model in the catalog needs between 80 GB and the 96 GB installed, so none runs only partly on the GPU.
Text models that run well within 80 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 191

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

Every reviewed text model here 37

Every one that runs here, well or slowly, scored or not; 19 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 2026-10-25, not by quality.

Reviewed text models that run on Mac Studio · M5 Ultra · 30-core CPU / 64-core GPU · 96 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 37

With 128 GB you also run… 2

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 80 GB: 144 run well · 2 tight · 10 reviewed · 4 more run slowly (4 of them run well with 128 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. All 4 vision models that would run well with 128 GB but not here already run here, slowly.
Vision models that run well within 80 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
gemma-3-27b-itgoogle · 27.43B · Image to text · LMArena 1,160Q4 · Hugging Face count · source1,160 ± 8~29 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
Molmo2-8Ballenai · 8.7B · Image to text · LMArena 1,112Q4 · Hugging Face count · source1,112 ± 20~15 GBQ4 · Hugging Face countsource
Molmo-72B-0924allenai · 73.31B · Image to text · LMArena 1,045Q4 · Hugging Face count · source1,045 ± 13~63 GBQ4 · Hugging Face countsource
Llama-3.2-90B-Vision-Instructmeta-llama · 88.6B · Image to text · LMArena 1,032Q4 · Hugging Face count · source1,032 ± 9~75 GBTight fit: Needs ~75 GB: runs well, about 5 GB left beyond the system reserveQ4 · Hugging Face countsource
8 of 146

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

Also runs slowly4 models

Above the macOS default GPU share (80 GB here, reserve included) but within the 96 GB installed: the rest runs on the CPU unless the limit is raised. Planning estimate, not a speed figure.

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

Image

76 within 80 GB · 1 more with 128 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 80 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
FLUX.2 [dev]Black Forest Labs · 32B · Image to image · LMArena 1,14616-bit est. · params · sourceNo comparable published result1,146 ± 4~79 GB16-bit est. · paramssource
Qwen-ImageQwen · 27.1B · Text to image · Image to image · LMArena 1,05716-bit est. · params · sourceNo comparable published result1,057 ± 3~68 GB16-bit est. · paramssource
Qwen-Image-EditQwen · 20.4B · Image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~51 GB16-bit est. · paramssource
Qwen-Image-Edit-2509Qwen · 20.4B · Image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~51 GB16-bit est. · paramssource
Qwen-Image-Edit-2511Qwen · 20.4B · Image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~51 GB16-bit est. · paramssource
Qwen-Image-LayeredQwen · 20.4B · Text + image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~51 GB16-bit est. · paramssource
8 of 76

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

With 128 GB you also run… 1

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

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

Video

71 within 80 GB · 1 more with 128 GB
Video models within 80 GB
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
LTX-2.3 FastLightricks · 22B · Text to video16-bit est. · params · source~55 GB16-bit est. · paramssource
LTX-2.3 ProLightricks · 22B · Text to video16-bit est. · params · source~55 GB16-bit est. · paramssource
LTX-2.5 FastLightricks · 22B · Text to video16-bit est. · params · source~55 GB16-bit est. · paramssource
8 of 71

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

With 128 GB you also run… 1

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

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

Audio

131 within 80 GB · 1 more with 128 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 80 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
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
personaplex-7b-v1nvidia · 8.4B · Speech to speech / audio to audio16-bit est. · params · sourceNo comparable published result~23 GB16-bit est. · paramssource
8 of 131

With 128 GB you also run… 1

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

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 80 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 80 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 80 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

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

Unified memory96 GBShared by CPU and GPU · source
Memory bandwidth1,200 GB/sManufacturer spec · not model speed · source
Launch price (MSRP)USD 5,499.00US · launched · source · not a tracked offer
Where to buyApple StoreManufacturer link · this configuration · 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 128 GB. Q4 planning estimates, not measured fits.

Reviewed · Manufacturer source

CPU cores
30
Processor
Apple M5 Ultra
GPU cores
64
Graphics processor
Apple M5 Ultra GPU
GPU runtime status
Not stated by the source
Memory capacity
96 GB
Memory kind
Unified memory
Memory bandwidth
1,200 GB/s
Bluetooth
Bluetooth 6
CPU performance cores
24
CPU super cores
12
Dimensions (cm)
19.7 × 19.7 × 9.5 (W × D × H)
Ethernet
10 Gb/s
Ethernet speeds
1 · 2.5 · 5 · 10
Front ports
2 × Thunderbolt 5 up to 120 Gb/s · SDXC UHS-II
Maximum continuous power
480 W
Media engine formats
H.264 · HEVC · ProRes · ProRes RAW · AV1 decode
Neural Engine cores
32
Power frequency
50–60 Hz, single phase
Operating system
macOS
Operating temperature
10–35 °C
Supply voltage
100–240 V AC
Ports
4 × Thunderbolt 5 (USB-C) · 2 × USB-A · HDMI 2.1 · 10Gb Ethernet · 3.5 mm headphone jack · 2 × front Thunderbolt 5 · SDXC UHS-II
Relative humidity
5–90% noncondensing
Release date
2026-09-22
Storage options
Base storage: 1 TB; configure-to-order options: 2 TB, 4 TB, 8 TB or 16 TB.
Storage temperature
−40–47 °C
Maximum Thunderbolt rate
120 Gb/s
Weight
3.6 kg
Wi-Fi
Wi-Fi 7 (802.11be)
Introduced
2026

Published base memory tier for the 2026 Mac Studio M5 Ultra family. Unified memory is shared across macOS, apps and GPU use; it is not dedicated GPU VRAM and does not establish model speed.

Photo: Apple Mac Studio family photo · internal configuration is not pictured. · Manufacturer source

Memory bandwidth is not measured model speed; verify runtime and checkpoint compatibility. Hardware specification reviewed: 2026-10-09.

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.