Can I run this LLM?

Can a NVIDIA RTX 5090 (32GB) run Gemma 4 31B?

Gemma · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 31B at Q3_K_M · 13.2 GB · 55–83 tok/s on a NVIDIA RTX 5090 (32GB).

Every quantization on this machine

Quant	Size	Speed	Fit
Q3_K_M	13.2 GB	55–83 tok/s	Runs great
Q4_K_M	18.6 GB	45–68 tok/s	Tight / slow
Q5_K_M	21.9 GB	41–61 tok/s	Won't fit
Q6_K	25.3 GB	37–55 tok/s	Won't fit
Q8_0	32.6 GB	31–46 tok/s	Won't fit
FP16	61.4 GB	18–28 tok/s	Won't fit

Ran Gemma 4 31B on a NVIDIA RTX 5090 (32GB)? Add your real numbers →