can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA B200 (192GB) run Gemma 4 12B?

Gemma · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 12B at FP16 · 23.8 GB · 138–208 tok/s on a NVIDIA B200 (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M5.1 GB246–369 tok/sRuns great
Q4_K_M7.2 GB227–340 tok/sRuns great
Q5_K_M8.5 GB216–324 tok/sRuns great
Q6_K9.8 GB206–309 tok/sRuns great
Q8_012.7 GB188–281 tok/sRuns great
FP1623.8 GB138–208 tok/sRuns great

Ran Gemma 4 12B on a NVIDIA B200 (192GB)? Add your real numbers →