can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5080 (16GB) run Gemma 4 12B?

Gemma · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 12B at Q6_K · 9.8 GB · 58–88 tok/s on a NVIDIA RTX 5080 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M5.7 GB88–133 tok/sRuns great
Q4_K_M7.1 GB75–112 tok/sRuns great
Q5_K_M8.4 GB66–99 tok/sRuns great
Q6_K9.8 GB58–88 tok/sRuns great
Q8_012.7 GB47–71 tok/sTight / slow
FP1623.8 GB27–41 tok/sWon't fit

Ran Gemma 4 12B on a NVIDIA RTX 5080 (16GB)? Add your real numbers →