Can I run this LLM?
Can a Mac Studio M3 Ultra (512GB) run Mistral Small 4 119B (MoE)?
Mistral · Apache 2.0 · estimated for a 512.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Mistral Small 4 119B (MoE) at FP16 · 238.0 GB · 34–51 tok/s on a Mac Studio M3 Ultra (512GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 54.4 GB | 87–130 tok/s | Runs great |
| Q4_K_M | 73.8 GB | 74–112 tok/s | Runs great |
| Q5_K_M | 89.2 GB | 67–100 tok/s | Runs great |
| Q6_K | 99.4 GB | 63–94 tok/s | Runs great |
| Q8_0 | 126.5 GB | 54–80 tok/s | Runs great |
| FP16 | 238.0 GB | 34–51 tok/s | Runs great |
Open the full calculator →Everything a Mac Studio M3 Ultra (512GB) runsMistral Small 4 119B (MoE) on other machinesWhat to buy to run it →
Ran Mistral Small 4 119B (MoE) on a Mac Studio M3 Ultra (512GB)? Add your real numbers →