Can I run this LLM?
Can a MacBook Pro M3 Pro (36GB) run Devstral Small 2 24B?
Mistral · See model card · estimated for a 36.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: Devstral Small 2 24B at Q2_K · 8.9 GB · 10–15 tok/s on a MacBook Pro M3 Pro (36GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 8.9 GB | 10–15 tok/s | Tight / slow |
| Q3_K_M | 11.5 GB | 8–12 tok/s | Tight / slow |
| Q4_K_M | 14.3 GB | 6–10 tok/s | Tight / slow |
| Q5_K_M | 16.8 GB | 6–8 tok/s | Tight / slow |
| Q6_K | 19.4 GB | 5–7 tok/s | Tight / slow |
| Q8_0 | 25.1 GB | 4–6 tok/s | Won't fit |
| FP16 | 47.2 GB | 2–3 tok/s | Won't fit |
Open the full calculator →Everything a MacBook Pro M3 Pro (36GB) runsDevstral Small 2 24B on other machinesWhat to buy to run it →
Ran Devstral Small 2 24B on a MacBook Pro M3 Pro (36GB)? Add your real numbers →