can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run Gemma 4 31B?

Gemma · Apache 2.0 · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 31B at FP16 · 61.4 GB · 18–28 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M13.2 GB55–83 tok/sRuns great
Q4_K_M18.6 GB45–68 tok/sRuns great
Q5_K_M21.9 GB41–61 tok/sRuns great
Q6_K25.3 GB37–55 tok/sRuns great
Q8_032.6 GB31–46 tok/sRuns great
FP1661.4 GB18–28 tok/sRuns great

Ran Gemma 4 31B on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →