Can I run this LLM?
Can a NVIDIA RTX 5090 (32GB) run Qwen3.5 9B?
Qwen · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.5 9B at FP16 · 17.9 GB · 60–90 tok/s on a NVIDIA RTX 5090 (32GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 3.9 GB | 165–248 tok/s | Runs great |
| Q4_K_M | 5.4 GB | 138–207 tok/s | Runs great |
| Q5_K_M | 6.4 GB | 126–189 tok/s | Runs great |
| Q6_K | 7.4 GB | 115–172 tok/s | Runs great |
| Q8_0 | 9.5 GB | 97–145 tok/s | Runs great |
| FP16 | 17.9 GB | 60–90 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA RTX 5090 (32GB) runsQwen3.5 9B on other machinesWhat to buy to run it →
Ran Qwen3.5 9B on a NVIDIA RTX 5090 (32GB)? Add your real numbers →