Can Mac Studio M5 Ultra 256 GB run Mistral Small 4 (119B-A6.5B)?
256 GB unified · 1228 GB/s memory bandwidth · Mistral Small 4 (119B-A6.5B) has 119.4B parameters (6.5B active per token).
Short answer
Yes, excellent for chat and excellent or better for every workload we test.
Best quantization for chat: 6-bit (91 GB of weights) on LM Studio. Generation: 65–110 tok/s, leaving about 154 GB free for your other apps.
How it rates for each workload
Same model and machine, different jobs. Agents and long documents send far bigger prompts than chat, so they need much more speed and memory.
| Workload | Verdict | Quant | Generation | First reply | Context | |
|---|---|---|---|---|---|---|
| Chatwith Open WebUI | Excellent | 6-bit | 65–110 tok/s | under 1 s | 8K | Details |
| Coding questionswith Continue | Excellent | 6-bit | 65–110 tok/s | ≈1 s | 16K | Details |
| Coding in a repositorywith Aider | Excellent | 8-bit | 50–80 tok/s | ≈3 s | 32K | Details |
| Agentic codingwith OpenCode | Excellent | 8-bit | 50–80 tok/s | ≈4 s | 32K | Details |
| Long documents (64K)with Open WebUI | Excellent | 6-bit | 55–90 tok/s | ≈15 s | 64K | Details |
Speeds are bandwidth-based estimates; no direct benchmark exists for this pair. “First reply” is the time to read the workload’s opening prompt. How we calculate
Get it running
Copy-paste commands for the 6-bit build with a 64K context. Ollama and llama.cpp download the file straight from Hugging Face.
ollama run hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q6_K_XL
This build is split into 4 files, which Ollama can't import from Hugging Face. Use llama.cpp or LM Studio instead.
Other models for Mac Studio M5 Ultra 256 GB
The best-rated models for chat on this machine.
- gpt-oss-120b120–210 tok/sExcellent
- Qwen3.6 35B-A3B140–240 tok/sExcellent
- Qwen3-Next 80B-A3B Instruct140–230 tok/sExcellent
- Gemma 4 26B-A4B110–190 tok/sExcellent
- Qwen3.5 35B-A3B140–240 tok/sExcellent
- LFM2.5 24B-A2B280–460 tok/sExcellent
Cheapest machines for Mistral Small 4 (119B-A6.5B)
Hardware rated comfortable or better for chat, lowest price first.
- Ryzen AI Max+ 395 mini PC / Framework Desktop · 128 GB$2,000 · 30–40 tok/sExcellent
- Mac Studio M2 Max 96 GB$3,799 · 50–65 tok/sExcellent
- MacBook Pro M3 Max 96 GB$3,999 · 40–50 tok/sExcellent
- Mac Studio M4 Max 128 GB$4,099 · 50–70 tok/sExcellent
- Mac Studio M5 Max 128 GB$4,099 · 50–85 tok/sExcellent
- MacBook Pro M2 Max 96 GB$5,099 · 50–65 tok/sExcellent
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.