can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA B200 (192GB) run Gemma 3 27B?

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

Yes — it runs great.

Best fit: Gemma 3 27B at FP16 · 54.0 GB · 82–123 tok/s on a NVIDIA B200 (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB206–309 tok/sRuns great
Q3_K_M13.4 GB187–280 tok/sRuns great
Q4_K_M16.6 GB170–255 tok/sRuns great
Q5_K_M19.3 GB158–237 tok/sRuns great
Q6_K22.2 GB146–220 tok/sRuns great
Q8_028.7 GB126–189 tok/sRuns great
FP1654.0 GB82–123 tok/sRuns great

Ran Gemma 3 27B on a NVIDIA B200 (192GB)? Add your real numbers →