Can I run this LLM?
Can a NVIDIA RTX 5090 (32GB) run Qwen3.8 27B?
Qwen · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.8 27B at Q6_K · 23.9 GB · 48–72 tok/s on a NVIDIA RTX 5090 (32GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 10.8 GB | 90–135 tok/s | Runs great |
| Q3_K_M | 13.4 GB | 77–115 tok/s | Runs great |
| Q4_K_M | 17.4 GB | 62–93 tok/s | Runs great |
| Q5_K_M | 20.9 GB | 53–80 tok/s | Runs great |
| Q6_K | 23.9 GB | 48–72 tok/s | Runs great |
| Q8_0 | 29.1 GB | 40–60 tok/s | Won't fit |
| FP16 | 54.7 GB | 23–34 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 5090 (32GB) runsQwen3.8 27B on other machinesWhat to buy to run it →
Ran Qwen3.8 27B on a NVIDIA RTX 5090 (32GB)? Add your real numbers →