can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA A100 (80GB) run Gemma 3 12B?

Gemma · Gemma · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 3 12B at FP16 · 23.5 GB · 51–77 tok/s on a NVIDIA A100 (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.8 GB144–215 tok/sRuns great
Q3_K_M6.0 GB128–193 tok/sRuns great
Q4_K_M7.3 GB116–174 tok/sRuns great
Q5_K_M8.5 GB106–159 tok/sRuns great
Q6_K9.7 GB98–147 tok/sRuns great
Q8_012.5 GB83–124 tok/sRuns great
FP1623.5 GB51–77 tok/sRuns great

Ran Gemma 3 12B on a NVIDIA A100 (80GB)? Add your real numbers →