can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI300X (192GB) run Qwen3 14B?

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

Yes — it runs great.

Best fit: Qwen3 14B at FP16 · 29.5 GB · 96–144 tok/s on a AMD Instinct MI300X (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.8 GB229–344 tok/sRuns great
Q3_K_M7.3 GB210–315 tok/sRuns great
Q4_K_M9.0 GB192–289 tok/sRuns great
Q5_K_M10.5 GB179–269 tok/sRuns great
Q6_K12.1 GB167–250 tok/sRuns great
Q8_015.7 GB145–217 tok/sRuns great
FP1629.5 GB96–144 tok/sRuns great

Ran Qwen3 14B on a AMD Instinct MI300X (192GB)? Add your real numbers →