Mac Studio M5 Ultra · 256 GB unified
Apple · Mac Studio · 2026
194 text models run well · 1,200 GB/s bandwidth
Models on this hardware
Start here
File UD-Q4_K_M · 16.9 GB · unsloth/gemma-4-26B-A4B-it-GGUF · What is Q4?
Memory Needs ~19 GB · ~27 GB on Mac Studio 2026 · M5 Ultra · 256 GB unified, including ~8 GB the system keeps
ollama run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M- Install Ollama
- Run the command above
- Ask:
Explain what a context window is, in two sentences.
File Q4_K_M · 16.5 GB · prithivMLmods/Smaug-Mini-GGUF · What is Q4?
Memory Needs ~21 GB · ~29 GB on Mac Studio 2026 · M5 Ultra · 256 GB unified, including ~8 GB the system keeps
ollama run hf.co/prithivMLmods/Smaug-Mini-GGUF:Q4_K_M- Install Ollama
- Run the command above
- Ask:
Explain what a context window is, in two sentences.
Text
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).
| Smaug MiniQ4 · published params · source | 76.9 | Not on the LMArena text leaderboard of 2026-10-22 | ~29 GB | Q4 · published params |
|---|---|---|---|---|
| Qwen3.8 27BQ4 · published params · source | 75.3 | 1,437 ± 5 | ~29 GB | Q4 · published params |
| Qwen3.6 27BQ4 · published params · source | 64.0 | Not on the LMArena text leaderboard of 2026-10-22 | ~29 GB | Q4 · published params |
| Qwen3 14BQ4 · published params · source | No comparable published result | Not on the LMArena text leaderboard of 2026-10-22 | ~20 GB | Q4 · published params |
| Gemma 4 31BQ4 · published params · source | No comparable published result | 1,452 ± 7 | ~32 GB | Q4 · published params |
| Gemma 4 26B A4BQ4 · published params · source | No comparable published result | 1,437 ± 7 | ~27 GB | Q4 · published params |
| Qwen3 8BQ4 · published params · source | No comparable published result | Not on the LMArena text leaderboard of 2026-10-22 | ~15 GB | Q4 · published params |
| Qwen3.5 9BQ4 · published params · source | No comparable published result | Not on the LMArena text leaderboard of 2026-10-22 | ~15 GB | Q4 · published params |
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.
| Qwen3 14B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~20 GB | 9.0 | Apache 2.0 | 10.4M |
|---|---|---|---|---|---|---|
| Gemma 4 31B | Not in LiveBench 2026-06-25 | 1,452 | ~32 GB | 18.3 | Apache 2.0 | 8.4M |
| Gemma 4 26B A4B | Not in LiveBench 2026-06-25 | 1,437 | ~27 GB | 16.9 | Apache 2.0 | 8.2M |
| Qwen3 8B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~15 GB | 5.0 | Apache 2.0 | 8.1M |
| Qwen3.8 27B | 75.3 | 1,437 | ~29 GB | 16.5 | Apache 2.0 | 7.8M |
| Qwen3.5 9B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~15 GB | 5.7 | Apache 2.0 | 6.1M |
| gpt-oss-20b | Not in LiveBench 2026-06-25 | 1,317 | ~24 GB | 11.6 | Apache 2.0 | 5.8M |
| Llama 3.1 8B Instruct | Not in LiveBench 2026-06-25 | 1,211 | ~14 GB | 4.9 | Llama 3.1 | 4.8M |
| Qwen3 1.7B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~10 GB | 1.1 | Apache 2.0 | 4.1M |
| Gemma 4 E4B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~14 GB | 5.0 | Apache 2.0 | 4M |
| Llama 3.2 1B Instruct | Not in LiveBench 2026-06-25 | 1,111 | ~9 GB | 0.8 | Llama 3.2 | 3.5M |
| Gemma 4 E2B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~12 GB | 3.1 | Apache 2.0 | 3M |
| Qwen3 4B Instruct 2507 | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~11 GB | 2.5 | Apache 2.0 | 2.6M |
| Qwen3.6 27B | 64.0 | Not on the LMArena text leaderboard of 2026-10-22 | ~29 GB | 16.8 | Apache 2.0 | 2.4M |
| Gemma 4 12B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~17 GB | 7.1 | Apache 2.0 | 1.7M |
| Qwen3.5 35B A3B | Not in LiveBench 2026-06-25 | 1,394 | ~35 GB | 22.0 | Apache 2.0 | 1.5M |
| Nemotron 3 Nano 30B A3B | Not in LiveBench 2026-06-25 | 1,314 | ~38 GB | 24.6 | NVIDIA Nemotron Open Model | 1.4M |
| Llama 3.2 3B Instruct | Not in LiveBench 2026-06-25 | 1,167 | ~11 GB | 2.0 | Llama 3.2 | 1.1M |
| Qwen3 30B A3B Instruct 2507 | Not in LiveBench 2026-06-25 | 1,382 | ~31 GB | 18.6 | Apache 2.0 | 1.1M |
| GLM-4.7 Flash | Not in LiveBench 2026-06-25 | 1,365 | ~31 GB | 18.3 | MIT | 953.7K |
| Nemotron 3.5 Lightning 30B A3B | Not in LiveBench 2026-06-25 | Arena rated the NVFP4 build, NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4); this entry is the BF16 reference, which NVIDIA reports with different scores | ~31 GB | 18.9 | OpenMDW 1.1 | 861.5K |
| Qwen3 Coder 30B A3B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~31 GB | 18.6 | Apache 2.0 | 745K |
| SmolLM3 3B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~11 GB | 1.9 | Apache 2.0 | 718.7K |
| Nemotron 3 Super 120B A12B | Not in LiveBench 2026-06-25 | Arena does not state the precision of the build it served, so no rating is matched to this NVFP4 checkpoint | ~98 GB | 82.5 | NVIDIA Nemotron Open Model | 535.1K |
| Phi-4 | Not in LiveBench 2026-06-25 | 1,256 | ~19 GB | 8.0 | MIT | 368.3K |
| DeepSeek R1 0528 Qwen3 8B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~15 GB | 5.0 | MIT | 355.8K |
| Phi-4 mini | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~11 GB | 2.5 | MIT | 342.8K |
| Olmo 3 7B Instruct | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~14 GB | 4.5 | Apache 2.0 | 262.5K |
| Devstral Small 2 24B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~26 GB | 14.3 | Apache 2.0 | 195.6K |
| Mistral Small 3.2 24B | Not in LiveBench 2026-06-25 | 1,356 | ~27 GB | 14.3 | Apache 2.0 | 181.4K |
| Ministral 3 14B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~19 GB | 8.2 | Apache 2.0 | 126.5K |
| Ministral 3 3B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~11 GB | 2.1 | Apache 2.0 | 87.4K |
| Ministral 3 8B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~15 GB | 5.2 | Apache 2.0 | 79.4K |
| Granite 4.2 8B | Not in LiveBench 2026-06-25 | 1,290 | ~14 GB | 5.3 | Apache 2.0 | 78.3K |
| Granite 4.2 3B | Not in LiveBench 2026-06-25 | 1,290 | ~11 GB | 2.2 | Apache 2.0 | 39.8K |
| Granite 4.2 30B | Not in LiveBench 2026-06-25 | 1,340 | ~31 GB | 17.7 | Apache 2.0 | 39.3K |
| Olmo 3 32B Think | Not in LiveBench 2026-06-25 | 1,306 | ~32 GB | 19.5 | Apache 2.0 | 13.1K |
| Ling 3.0 Flash | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | ~101 GB | 77.8 | MIT | 9.7K |
| Smaug Mini | 76.9 | Not on the LMArena text leaderboard of 2026-10-22 | ~29 GB | 16.5 | Apache 2.0 | 817 |
| GLM-5.3 Flash | 71.6 | 1,476 | ~248 GBRuns slowly | 156.8 | MIT | 6.4M |
| DeepSeek V4 Flash · 0731 | 74.2 | Not on the LMArena text leaderboard of 2026-10-22 | ~236 GBRuns slowly | 136.7 | MIT | 4.1M |
| DeepSeek V4 Flash | 65.5 | 1,436 | ~221 GBRuns slowly | 137.9 | MIT | 936.1K |
| MiMo V2.6 Flash | Not in LiveBench 2026-06-25 | 1,448 | ~240 GBRuns slowly | 126.4 | MIT | 89.6K |
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.
- MiniMax M3MiniMax~329 GBQ4 · published params
- Llama-3.1-405Bmeta-llama~313 GBQ4 · tensor count
- Llama-3.1-405B-Instructmeta-llama~313 GBQ4 · tensor count
- Qwen3-Coder-480B-A35B-InstructQwen~369 GBQ4 · tensor count
Adjust the estimate: quantization, context, reserve
Vision
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.
| Gemma 4 31BQ4 · published params · source | 1,262 ± 6 | ~32 GB | Q4 · published params |
|---|---|---|---|
| Qwen3.8 27BQ4 · published params · source | 1,242 ± 8 | ~29 GB | Q4 · published params |
| Gemma 4 26B A4BQ4 · published params · source | 1,242 ± 6 | ~27 GB | Q4 · published params |
| Qwen3-VL-235B-A22B-InstructQ4 · Hugging Face count · source | 1,215 ± 7 | ~185 GBTight fit: Needs ~185 GB: runs well, about 15 GB left beyond the system reserve | Q4 · Hugging Face count |
| gemma-3-27b-itQ4 · Hugging Face count · source | 1,160 ± 8 | ~29 GB | Q4 · Hugging Face count |
| GLM-4.5VQ4 · Hugging Face count · source | 1,153 ± 12 | ~89 GB | Q4 · Hugging Face count |
| Llama-4-Scout-17B-16E-InstructQ4 · Hugging Face count · source | 1,128 ± 10 | ~90 GB | Q4 · Hugging Face count |
| Qwen2.5-VL-32B-InstructQ4 · Hugging Face count · source | 1,119 ± 15 | ~34 GB | Q4 · Hugging Face count |
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 slowly
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.
- MiniMax M3MiniMax~329 GBQ4 · published params
- Llama-4-Maverick-17B-128Emeta-llama~310 GBQ4 · Hugging Face count
- Llama-4-Maverick-17B-128E-Instructmeta-llama~310 GBQ4 · Hugging Face count
12 more vision models in the catalog have no usable memory figure or parameter count for this profile. Browse Vision models
Image
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.
| Stable Diffusion XL 1.0Platform path documented · Apple Core ML · source | 0.55 | Not on the LMArena text-to-image leaderboard of 2026-10-07 | Documented path without a memory figure | Platform path documented |
|---|---|---|---|---|
| Stable Diffusion 1.5Platform path documented · Apple Core ML · source | 0.43 | Not on the LMArena text-to-image leaderboard of 2026-10-07 | Documented path without a memory figure | Platform path documented |
| HunyuanImage 3.0 (Fal)16-bit est. · params · source | No comparable published result | 1,150 ± 3 | ~194 GB | 16-bit est. · params |
| HunyuanImage 3.0 Instruct (Fal)16-bit est. · params · source | No comparable published result | Arena rated hunyuan-image-3.0; this entry is the Instruct checkpoint | ~194 GB | 16-bit est. · params |
| Cosmos3-Super-Text2Image16-bit est. · params · source | No comparable published result | 1,152 ± 6 | ~156 GB | 16-bit est. · params |
| Cosmos3-Super-Text2Image (agentic)16-bit est. · params · source | No comparable published result | 1,165 ± 7 | ~156 GB | 16-bit est. · params |
| Cosmos3-Super-Text2Image-4Step16-bit est. · params · source | No comparable published result | Arena rated Cosmos3-Super-Text2Image; this entry is the 4-step distilled checkpoint | ~156 GB | 16-bit est. · params |
| Emu3.5-Image16-bit est. · params · source | No comparable published result | Not reviewed for LMArena | ~84 GB | 16-bit est. · params |
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
| Cosmos3-Super-Image2Video16-bit est. · params · source | ~158 GB | 16-bit est. · params |
|---|---|---|
| Cosmos3-Super-Image2Video-4Step16-bit est. · params · source | ~156 GB | 16-bit est. · params |
| MiniMax H316-bit est. · params · source | ~82 GB | 16-bit est. · params |
| Kandinsky-6.0-Pro-distill-5s-Diffusers16-bit est. · params · source | ~75 GB | 16-bit est. · params |
| stepvideo-t2v16-bit est. · params · source | ~73 GB | 16-bit est. · params |
| stepvideo-ti2v16-bit est. · params · source | ~73 GB | 16-bit est. · params |
| Wan2.2 T2V-A14B16-bit est. · params · source | ~67 GB | 16-bit est. · params |
| Wan2.2-I2V-A14B16-bit est. · params · source | ~67 GB | 16-bit est. · params |
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
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.
| Whisper large-v3-turboPlatform path documented · whisper.cpp / Metal · source | 7.83 | Documented path without a memory figure | Platform path documented |
|---|---|---|---|
| Whisper large-v3Platform path documented · whisper.cpp / Metal · source | 7.44 | Documented path without a memory figure | Platform path documented |
| Step-Audio-R1.116-bit est. · params · source | No comparable published result | ~83 GB | 16-bit est. · params |
| Voxtral-Small-24B-250716-bit est. · params · source | No comparable published result | ~61 GB | 16-bit est. · params |
| Kimi-Audio-7B16-bit est. · params · source | No comparable published result | ~26 GB | 16-bit est. · params |
| Kimi-Audio-7B-Instruct16-bit est. · params · source | No comparable published result | ~26 GB | 16-bit est. · params |
| Llasa-8B16-bit est. · params · source | No comparable published result | ~23 GB | 16-bit est. · params |
| MOSS-TTS-v1.516-bit est. · params · source | No comparable published result | ~23 GB | 16-bit est. · params |
35 more audio models in the catalog have no usable memory figure or parameter count for this profile. Browse Audio models
Embeddings
Embeddings · MTEB (Multilingual, v2) · mean(task)
0–100 · higher is better
- Color = publisher
| Qwen3-Embedding 8B8-bit · published params · source | 70.6 | ~12 GB | 8-bit · published params |
|---|---|---|---|
| Qwen3-Embedding 4B8-bit · published params · source | 69.5 | ~7 GB | 8-bit · published params |
| Harrier OSS v1 (0.6B)8-bit · published params · source | 69.0 | ~3 GB | 8-bit · published params |
| Qwen3-Embedding 0.6B8-bit · published params · source | 64.3 | ~3 GB | 8-bit · published params |
| Multilingual E5 Large Instruct8-bit · published params · source | 63.2 | ~3 GB | 8-bit · published params |
| EmbeddingGemma 28-bit · published params · source | 61.4 | ~3 GB | 8-bit · published params |
| EmbeddingGemma (300M)8-bit · published params · source | 61.1 | ~3 GB | 8-bit · published params |
| BGE-M38-bit · published params · source | 59.6 | ~3 GB | 8-bit · published params |
Runs well within 200 GB of unified memory · planning estimates, not measured speed
Measurements
Speed on this hardware
We 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
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
- Weight
- 3.6 kg
- 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.
Less memory · 128 GB 8
- Ascent GX10 · NVIDIA GB10 · 128 GB unified
- Dell Pro Max with GB10 (FCM1253) · NVIDIA GB10 · 128 GB unified
- DGX Spark · 128 GB unified
- Framework Desktop · Ryzen AI Max+ 395 · 128 GB
- HP Z2 Mini G1a · Ryzen AI Max+ PRO 395 · 128 GB unified
- HP ZGX Nano G1n AI Station · NVIDIA GB10 · 128 GB unified
- MacBook Pro 14-inch · M5 Max · 18-core CPU / 40-core GPU · 128 GB unified
- MacBook Pro 16-inch · M5 Max · 18-core CPU / 40-core GPU · 128 GB unified
