Can I run this LLM?
Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run Devstral Small 2 24B?
Mistral · See model card · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Devstral Small 2 24B at Q3_K_M · 11.5 GB · 13–20 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 8.9 GB | 16–25 tok/s | Runs great |
| Q3_K_M | 11.5 GB | 13–20 tok/s | Runs great |
| Q4_K_M | 14.3 GB | 11–16 tok/s | Tight / slow |
| Q5_K_M | 16.8 GB | 9–14 tok/s | Tight / slow |
| Q6_K | 19.4 GB | 8–12 tok/s | Tight / slow |
| Q8_0 | 25.1 GB | 6–10 tok/s | Tight / slow |
| FP16 | 47.2 GB | 4–5 tok/s | Tight / slow |
Open the full calculator →Everything a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) runsDevstral Small 2 24B on other machinesWhat to buy to run it →
Ran Devstral Small 2 24B on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →