can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4090 (24GB) run Qwen3 32B?

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

Yes — it runs great.

Best fit: Qwen3 32B at Q3_K_M · 16.0 GB · 39–59 tok/s on a NVIDIA RTX 4090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.3 GB48–72 tok/sRuns great
Q3_K_M16.0 GB39–59 tok/sRuns great
Q4_K_M19.8 GB33–49 tok/sWon't fit
Q5_K_M23.2 GB28–42 tok/sWon't fit
Q6_K26.9 GB25–37 tok/sWon't fit
Q8_034.8 GB20–29 tok/sWon't fit
FP1665.5 GB11–16 tok/sWon't fit

Ran Qwen3 32B on a NVIDIA RTX 4090 (24GB)? Add your real numbers →