can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Mistral Small 4 119B (MoE)?

Mistral · Apache 2.0 · estimated for a 144.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Mistral Small 4 119B (MoE) at FP16 · 238.0 GB · 39–58 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M54.4 GB278–418 tok/sRuns great
Q4_K_M73.8 GB257–386 tok/sRuns great
Q5_K_M89.2 GB243–364 tok/sRuns great
Q6_K99.4 GB234–351 tok/sRuns great
Q8_0126.5 GB214–320 tok/sRuns great
FP16238.0 GB39–58 tok/sRuns great

Ran Mistral Small 4 119B (MoE) on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →