can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run Gemma 4 12B?

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

Yes — it runs great.

Best fit: Gemma 4 12B at FP16 · 23.8 GB · 44–66 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M5.1 GB115–173 tok/sRuns great
Q4_K_M7.2 GB97–146 tok/sRuns great
Q5_K_M8.5 GB89–134 tok/sRuns great
Q6_K9.8 GB82–123 tok/sRuns great
Q8_012.7 GB70–104 tok/sRuns great
FP1623.8 GB44–66 tok/sRuns great

Ran Gemma 4 12B on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →