Can I run this LLM?
Can a Mac Studio M5 Ultra (512GB) run Qwen3.6 27B?
Qwen · Apache 2.0 · estimated for a 512.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.6 27B at FP16 · 53.8 GB · 14–21 tok/s on a Mac Studio M5 Ultra (512GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 11.9 GB | 49–73 tok/s | Runs great |
| Q3_K_M | 13.6 GB | 44–66 tok/s | Runs great |
| Q4_K_M | 16.8 GB | 38–57 tok/s | Runs great |
| Q5_K_M | 19.5 GB | 34–50 tok/s | Runs great |
| Q6_K | 22.5 GB | 30–45 tok/s | Runs great |
| Q8_0 | 28.6 GB | 25–37 tok/s | Runs great |
| FP16 | 53.8 GB | 14–21 tok/s | Runs great |
Open the full calculator →Everything a Mac Studio M5 Ultra (512GB) runsQwen3.6 27B on other machinesWhat to buy to run it →
Ran Qwen3.6 27B on a Mac Studio M5 Ultra (512GB)? Add your real numbers →