Can I run this LLM?
Can a Mac Studio M5 Ultra (256GB) run Devstral Small 2 24B?
Mistral · See model card · estimated for a 256.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Devstral Small 2 24B at FP16 · 47.2 GB · 16–24 tok/s on a Mac Studio M5 Ultra (256GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 8.9 GB | 58–86 tok/s | Runs great |
| Q3_K_M | 11.5 GB | 49–73 tok/s | Runs great |
| Q4_K_M | 14.3 GB | 42–63 tok/s | Runs great |
| Q5_K_M | 16.8 GB | 37–56 tok/s | Runs great |
| Q6_K | 19.4 GB | 33–50 tok/s | Runs great |
| Q8_0 | 25.1 GB | 27–41 tok/s | Runs great |
| FP16 | 47.2 GB | 16–24 tok/s | Runs great |
Open the full calculator →Everything a Mac Studio M5 Ultra (256GB) runsDevstral Small 2 24B on other machinesWhat to buy to run it →
Ran Devstral Small 2 24B on a Mac Studio M5 Ultra (256GB)? Add your real numbers →