can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI300X (192GB) run Qwen3 32B?

Qwen · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3 32B at FP16 · 65.5 GB · 51–76 tok/s on a AMD Instinct MI300X (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.3 GB163–244 tok/sRuns great
Q3_K_M16.0 GB141–212 tok/sRuns great
Q4_K_M19.8 GB124–186 tok/sRuns great
Q5_K_M23.2 GB112–168 tok/sRuns great
Q6_K26.9 GB101–152 tok/sRuns great
Q8_034.8 GB84–126 tok/sRuns great
FP1665.5 GB51–76 tok/sRuns great

Ran Qwen3 32B on a AMD Instinct MI300X (192GB)? Add your real numbers →