can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4080 (16GB) run Gemma 4 E4B?

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

Yes — it runs great.

Best fit: Gemma 4 E4B at Q8_0 · 8.2 GB · 82–122 tok/s on a NVIDIA RTX 4080 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M4.1 GB132–197 tok/sRuns great
Q4_K_M5.0 GB116–174 tok/sRuns great
Q5_K_M5.5 GB109–163 tok/sRuns great
Q6_K7.1 GB91–136 tok/sRuns great
Q8_08.2 GB82–122 tok/sRuns great
FP1615.1 GB50–75 tok/sWon't fit

Ran Gemma 4 E4B on a NVIDIA RTX 4080 (16GB)? Add your real numbers →