Written by Jakub Rusinowski · Last updated March 17, 2025
Yes — comfortably
Yes, comfortably — Mistral Small 3.1 24B at Q8_0 needs about 27.2 GB of the 144 GB usable on Mac Studio (M2 Ultra, 192 GB), leaving ~116.8 GB spare and running at ~16.2 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~16.2 tok/s
| Usable memory for models | 144 GB |
| Memory bandwidth | 800 GB/s |
| Form factor | Desktop |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
| Quant | Memory needed | Fits 144 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 49.3 GB | ✓ Yes | 64K | ~8.9 tok/s | 47.2 GB |
| Q8_0 | 27.2 GB | ✓ Yes | 64K | ~16.2 tok/s | 25.1 GB |
| Q6_K | 21.5 GB | ✓ Yes | 64K | ~20.5 tok/s | 19.4 GB |
| Q5_K_M | 18.9 GB | ✓ Yes | 64K | ~23.4 tok/s | 16.7 GB |
| Q4_K_M | 16.4 GB | ✓ Yes | 64K | ~27 tok/s | 14.2 GB |
| Q3_K_M | 12.2 GB | ✓ Yes | 64K | ~36.4 tok/s | 10.1 GB |
| Q2_K | 9.9 GB | ✓ Yes | 64K | ~45 tok/s | 7.8 GB |
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Yes, comfortably — Mistral Small 3.1 24B at Q8_0 needs about 27.2 GB of the 144 GB usable on Mac Studio (M2 Ultra, 192 GB), leaving ~116.8 GB spare and running at ~16.2 tok/s (estimated), with room for about 65,536 tokens of context.
Q8_0 — it needs about 27.2 GB of the 144 GB available, downloads as roughly 25.1 GB, and runs at an estimated 16.2 tokens/sec with up to 64K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
← Can I Run It? | Mistral Small 3.1 model page | Check your hardware