can-i-run-this-llm

Can I run this LLM?

Can a Desktop CPU, DDR5 dual-channel (32GB) run Devstral Small 2 24B?

Mistral · See model card · estimated for a 32.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Devstral Small 2 24B at Q2_K · 8.9 GB · 3–5 tok/s on a Desktop CPU, DDR5 dual-channel (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K8.9 GB3–5 tok/sTight / slow
Q3_K_M11.5 GB3–4 tok/sTight / slow
Q4_K_M14.3 GB2–3 tok/sTight / slow
Q5_K_M16.8 GB2–3 tok/sTight / slow
Q6_K19.4 GB2–2 tok/sTight / slow
Q8_025.1 GB1–2 tok/sWon't fit
FP1647.2 GB1–1 tok/sWon't fit

Ran Devstral Small 2 24B on a Desktop CPU, DDR5 dual-channel (32GB)? Add your real numbers →