Can I run this LLM?
Can a NVIDIA RTX 5090 (32GB) run Qwen3 8B?
Qwen · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3 8B at FP16 · 16.4 GB · 64–96 tok/s on a NVIDIA RTX 5090 (32GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 3.3 GB | 177–265 tok/s | Runs great |
| Q3_K_M | 4.1 GB | 159–238 tok/s | Runs great |
| Q4_K_M | 5.0 GB | 143–215 tok/s | Runs great |
| Q5_K_M | 5.9 GB | 132–197 tok/s | Runs great |
| Q6_K | 6.7 GB | 121–181 tok/s | Runs great |
| Q8_0 | 8.7 GB | 102–154 tok/s | Runs great |
| FP16 | 16.4 GB | 64–96 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA RTX 5090 (32GB) runsQwen3 8B on other machinesWhat to buy to run it →
Ran Qwen3 8B on a NVIDIA RTX 5090 (32GB)? Add your real numbers →