can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4070 (12GB) run Devstral Small 2 24B?

Mistral · See model card · estimated for a 12.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Devstral Small 2 24B at Q2_K · 8.9 GB · 35–53 tok/s on a NVIDIA RTX 4070 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K8.9 GB35–53 tok/sTight / slow
Q3_K_M11.5 GB28–42 tok/sWon't fit
Q4_K_M14.3 GB23–35 tok/sWon't fit
Q5_K_M16.8 GB20–30 tok/sWon't fit
Q6_K19.4 GB18–27 tok/sWon't fit
Q8_025.1 GB14–21 tok/sWon't fit
FP1647.2 GB8–11 tok/sWon't fit
Open the full calculator →Everything a NVIDIA RTX 4070 (12GB) runsDevstral Small 2 24B on other machinesWhat to buy to run it →

Ran Devstral Small 2 24B on a NVIDIA RTX 4070 (12GB)? Add your real numbers →