Can I run this LLM?
Can a NVIDIA A100 (80GB) run Qwen3.6 27B?
Qwen · Apache 2.0 · estimated for a 80.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.6 27B at FP16 · 53.8 GB · 26–38 tok/s on a NVIDIA A100 (80GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 11.6 GB | 90–135 tok/s | Runs great |
| Q4_K_M | 16.3 GB | 70–105 tok/s | Runs great |
| Q5_K_M | 19.2 GB | 62–93 tok/s | Runs great |
| Q6_K | 22.2 GB | 55–83 tok/s | Runs great |
| Q8_0 | 28.6 GB | 45–67 tok/s | Runs great |
| FP16 | 53.8 GB | 26–38 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA A100 (80GB) runsQwen3.6 27B on other machinesWhat to buy to run it →
Ran Qwen3.6 27B on a NVIDIA A100 (80GB)? Add your real numbers →