Can I run this LLM?
Can a NVIDIA RTX 3090 (24GB) run Qwen3.6 27B?
Qwen · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.6 27B at Q4_K_M · 16.8 GB · 35–52 tok/s on a NVIDIA RTX 3090 (24GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 13.6 GB | 42–63 tok/s | Runs great |
| Q4_K_M | 16.8 GB | 35–52 tok/s | Runs great |
| Q5_K_M | 19.5 GB | 31–46 tok/s | Tight / slow |
| Q6_K | 22.5 GB | 27–41 tok/s | Won't fit |
| Q8_0 | 28.6 GB | 22–33 tok/s | Won't fit |
| FP16 | 53.8 GB | 12–18 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 3090 (24GB) runsQwen3.6 27B on other machinesWhat to buy to run it →
Ran Qwen3.6 27B on a NVIDIA RTX 3090 (24GB)? Add your real numbers →