can-i-run-this-llm

Can I run this LLM?

Can a AMD RX 7900 XTX (24GB) run Qwen3 30B-A3B (MoE)?

Qwen · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3 30B-A3B (MoE) at Q3_K_M · 13.2 GB · 195–293 tok/s on a AMD RX 7900 XTX (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K9.9 GB214–321 tok/sRuns great
Q3_K_M13.2 GB195–293 tok/sRuns great
Q4_K_M18.5 GB171–256 tok/sTight / slow
Q5_K_M21.8 GB159–238 tok/sWon't fit
Q6_K25.2 GB147–221 tok/sWon't fit
Q8_032.4 GB128–193 tok/sWon't fit
FP1661.1 GB85–128 tok/sWon't fit

Ran Qwen3 30B-A3B (MoE) on a AMD RX 7900 XTX (24GB)? Add your real numbers →