can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run Qwen3.5 4B?

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

Yes — it runs great.

Best fit: Qwen3.5 4B at FP16 · 8.4 GB · 236–354 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M2.3 GB312–468 tok/sRuns great
Q4_K_M2.7 GB305–457 tok/sRuns great
Q5_K_M3.1 GB299–448 tok/sRuns great
Q6_K3.5 GB293–439 tok/sRuns great
Q8_04.5 GB280–420 tok/sRuns great
FP168.4 GB236–354 tok/sRuns great

Ran Qwen3.5 4B on a AMD Instinct MI355X (288GB)? Add your real numbers →