Can I run this LLM?
Can a AMD Instinct MI355X (288GB) run Qwen3.6 27B?
Qwen · Apache 2.0 · estimated for a 288.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.6 27B at FP16 · 53.8 GB · 84–126 tok/s on a AMD Instinct MI355X (288GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 11.9 GB | 209–314 tok/s | Runs great |
| Q3_K_M | 13.6 GB | 197–296 tok/s | Runs great |
| Q4_K_M | 16.8 GB | 178–267 tok/s | Runs great |
| Q5_K_M | 19.5 GB | 165–247 tok/s | Runs great |
| Q6_K | 22.5 GB | 152–228 tok/s | Runs great |
| Q8_0 | 28.6 GB | 131–197 tok/s | Runs great |
| FP16 | 53.8 GB | 84–126 tok/s | Runs great |
Open the full calculator →Everything a AMD Instinct MI355X (288GB) runsQwen3.6 27B on other machinesWhat to buy to run it →
Ran Qwen3.6 27B on a AMD Instinct MI355X (288GB)? Add your real numbers →