can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run Gemma 4 31B?

Gemma · Apache 2.0 · estimated for a 288.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 31B at FP16 · 61.4 GB · 75–113 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M14.7 GB185–277 tok/sRuns great
Q4_K_M18.3 GB166–249 tok/sRuns great
Q5_K_M21.7 GB152–228 tok/sRuns great
Q6_K25.2 GB139–209 tok/sRuns great
Q8_032.6 GB118–178 tok/sRuns great
FP1661.4 GB75–113 tok/sRuns great

Ran Gemma 4 31B on a AMD Instinct MI355X (288GB)? Add your real numbers →