can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run Gemma 2 2B?

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

Yes — it runs great.

Best fit: Gemma 2 2B at Q8_0 · 2.8 GB · 306–459 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M1.6 GB326–489 tok/sRuns great
Q5_K_M1.9 GB321–482 tok/sRuns great
Q6_K2.2 GB316–474 tok/sRuns great
Q8_02.8 GB306–459 tok/sRuns great

Ran Gemma 2 2B on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →