Can I run this LLM?
Can a Mac Studio M2 Ultra (64GB) run Qwen3.8 27B?
Qwen · Apache 2.0 · estimated for a 64.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.8 27B at Q8_0 · 29.0 GB · 16–24 tok/s on a Mac Studio M2 Ultra (64GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 11.8 GB | 34–51 tok/s | Runs great |
| Q4_K_M | 16.6 GB | 26–39 tok/s | Runs great |
| Q5_K_M | 19.5 GB | 23–34 tok/s | Runs great |
| Q6_K | 22.5 GB | 20–30 tok/s | Runs great |
| Q8_0 | 29.0 GB | 16–24 tok/s | Runs great |
| FP16 | 54.6 GB | 9–14 tok/s | Won't fit |
Open the full calculator →Everything a Mac Studio M2 Ultra (64GB) runsQwen3.8 27B on other machinesWhat to buy to run it →
Ran Qwen3.8 27B on a Mac Studio M2 Ultra (64GB)? Add your real numbers →