can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run MiniCPM5 2B?

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

Yes — it runs great.

Best fit: MiniCPM5 2B at FP16 · 5.0 GB · 277–416 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K1.0 GB342–513 tok/sRuns great
Q3_K_M1.2 GB337–506 tok/sRuns great
Q4_K_M1.6 GB330–495 tok/sRuns great
Q5_K_M1.9 GB325–487 tok/sRuns great
Q6_K2.1 GB321–482 tok/sRuns great
Q8_02.7 GB312–468 tok/sRuns great
FP165.0 GB277–416 tok/sRuns great

Ran MiniCPM5 2B on a AMD Instinct MI355X (288GB)? Add your real numbers →