can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run Gemma 4 12B?

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

Yes — it runs great.

Best fit: Gemma 4 12B at FP16 · 23.8 GB · 146–220 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M5.7 GB266–399 tok/sRuns great
Q4_K_M7.1 GB250–375 tok/sRuns great
Q5_K_M8.4 GB237–356 tok/sRuns great
Q6_K9.8 GB225–337 tok/sRuns great
Q8_012.7 GB203–304 tok/sRuns great
FP1623.8 GB146–220 tok/sRuns great

Ran Gemma 4 12B on a AMD Instinct MI355X (288GB)? Add your real numbers →