Can I run this LLM?
Can a NVIDIA RTX 4060 Ti (16GB) run Devstral Small 2 24B?
Mistral · See model card · estimated for a 16.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Devstral Small 2 24B at Q3_K_M · 11.5 GB · 17–25 tok/s on a NVIDIA RTX 4060 Ti (16GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 8.9 GB | 21–31 tok/s | Runs great |
| Q3_K_M | 11.5 GB | 17–25 tok/s | Runs great |
| Q4_K_M | 14.3 GB | 14–20 tok/s | Won't fit |
| Q5_K_M | 16.8 GB | 12–18 tok/s | Won't fit |
| Q6_K | 19.4 GB | 10–15 tok/s | Won't fit |
| Q8_0 | 25.1 GB | 8–12 tok/s | Won't fit |
| FP16 | 47.2 GB | 4–7 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 4060 Ti (16GB) runsDevstral Small 2 24B on other machinesWhat to buy to run it →
Ran Devstral Small 2 24B on a NVIDIA RTX 4060 Ti (16GB)? Add your real numbers →