can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA A100 (80GB) run Mistral Small 4 119B (MoE)?

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

Yes — it runs great.

Best fit: Mistral Small 4 119B (MoE) at Q3_K_M · 54.4 GB · 208–312 tok/s on a NVIDIA A100 (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M54.4 GB208–312 tok/sRuns great
Q4_K_M73.8 GB181–272 tok/sWon't fit
Q5_K_M89.2 GB165–247 tok/sWon't fit
Q6_K99.4 GB155–233 tok/sWon't fit
Q8_0126.5 GB135–202 tok/sWon't fit
FP16238.0 GB87–131 tok/sWon't fit

Ran Mistral Small 4 119B (MoE) on a NVIDIA A100 (80GB)? Add your real numbers →