can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run Qwen3 14B?

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

Yes — it runs great.

Best fit: Qwen3 14B at FP16 · 29.5 GB · 128–191 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.8 GB262–393 tok/sRuns great
Q3_K_M7.3 GB245–368 tok/sRuns great
Q4_K_M9.0 GB229–344 tok/sRuns great
Q5_K_M10.5 GB217–325 tok/sRuns great
Q6_K12.1 GB204–307 tok/sRuns great
Q8_015.7 GB182–273 tok/sRuns great
FP1629.5 GB128–191 tok/sRuns great

Ran Qwen3 14B on a AMD Instinct MI355X (288GB)? Add your real numbers →