Can I run this LLM?

Can a AMD RX 7900 XTX (24GB) run Gemma 4 31B?

Gemma · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Gemma 4 31B at Q3_K_M · 13.2 GB · 32–48 tok/s on a AMD RX 7900 XTX (24GB).

Every quantization on this machine

Quant	Size	Speed	Fit
Q3_K_M	13.2 GB	32–48 tok/s	Tight / slow
Q4_K_M	18.6 GB	26–39 tok/s	Won't fit
Q5_K_M	21.9 GB	23–34 tok/s	Won't fit
Q6_K	25.3 GB	21–31 tok/s	Won't fit
Q8_0	32.6 GB	17–26 tok/s	Won't fit
FP16	61.4 GB	10–15 tok/s	Won't fit

Ran Gemma 4 31B on a AMD RX 7900 XTX (24GB)? Add your real numbers →