can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run Gemma 4 31B?

Gemma · Apache 2.0 · estimated for a 141.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 31B at FP16 · 61.4 GB · 49–74 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M14.7 GB139–208 tok/sRuns great
Q4_K_M18.3 GB122–182 tok/sRuns great
Q5_K_M21.7 GB109–164 tok/sRuns great
Q6_K25.2 GB98–148 tok/sRuns great
Q8_032.6 GB82–122 tok/sRuns great
FP1661.4 GB49–74 tok/sRuns great

Ran Gemma 4 31B on a NVIDIA H200 (141GB)? Add your real numbers →