can-i-run-this-llm

Can I run this LLM?

Can a AMD RX 7900 XTX (24GB) run Qwen3.5 9B?

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

Yes — it runs great.

Best fit: Qwen3.5 9B at FP16 · 17.9 GB · 35–52 tok/s on a AMD RX 7900 XTX (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M3.9 GB112–168 tok/sRuns great
Q4_K_M5.4 GB90–135 tok/sRuns great
Q5_K_M6.4 GB80–120 tok/sRuns great
Q6_K7.4 GB72–108 tok/sRuns great
Q8_09.5 GB59–89 tok/sRuns great
FP1617.9 GB35–52 tok/sRuns great

Ran Qwen3.5 9B on a AMD RX 7900 XTX (24GB)? Add your real numbers →