can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run Gemma 3 12B?

Gemma · Gemma · estimated for a 288.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 3 12B at FP16 · 23.5 GB · 143–215 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.8 GB263–394 tok/sRuns great
Q3_K_M6.0 GB249–374 tok/sRuns great
Q4_K_M7.3 GB236–354 tok/sRuns great
Q5_K_M8.5 GB226–339 tok/sRuns great
Q6_K9.7 GB216–324 tok/sRuns great
Q8_012.5 GB195–293 tok/sRuns great
FP1623.5 GB143–215 tok/sRuns great

Ran Gemma 3 12B on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →