can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA A100 (80GB) run Mistral Small 3.2 24B?

Mistral · Apache 2.0 · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Mistral Small 3.2 24B at FP16 · 47.2 GB · 29–43 tok/s on a NVIDIA A100 (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K8.9 GB110–165 tok/sRuns great
Q3_K_M11.5 GB93–139 tok/sRuns great
Q4_K_M14.3 GB79–118 tok/sRuns great
Q5_K_M16.8 GB70–105 tok/sRuns great
Q6_K19.4 GB62–94 tok/sRuns great
Q8_025.1 GB50–76 tok/sRuns great
FP1647.2 GB29–43 tok/sRuns great

Ran Mistral Small 3.2 24B on a NVIDIA A100 (80GB)? Add your real numbers →