Can I run this LLM?
Can a AMD Instinct MI355X (288GB) run Qwen3.8 27B?
Qwen · Apache 2.0 · estimated for a 288.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.8 27B at FP16 · 54.7 GB · 82–123 tok/s on a AMD Instinct MI355X (288GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 13.8 GB | 191–286 tok/s | Runs great |
| Q4_K_M | 17.1 GB | 172–258 tok/s | Runs great |
| Q5_K_M | 19.8 GB | 160–239 tok/s | Runs great |
| Q6_K | 22.9 GB | 147–221 tok/s | Runs great |
| Q8_0 | 29.1 GB | 128–192 tok/s | Runs great |
| FP16 | 54.7 GB | 82–123 tok/s | Runs great |
Open the full calculator →Everything a AMD Instinct MI355X (288GB) runsQwen3.8 27B on other machinesWhat to buy to run it →
Ran Qwen3.8 27B on a AMD Instinct MI355X (288GB)? Add your real numbers →