Can I run this LLM?
Can a MacBook Pro M3 Pro (36GB) run Qwen3.6 27B?
Qwen · Apache 2.0 · estimated for a 36.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: Qwen3.6 27B at Q3_K_M · 11.6 GB · 8–11 tok/s on a MacBook Pro M3 Pro (36GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 11.6 GB | 8–11 tok/s | Tight / slow |
| Q4_K_M | 16.3 GB | 6–8 tok/s | Tight / slow |
| Q5_K_M | 19.2 GB | 5–7 tok/s | Tight / slow |
| Q6_K | 22.2 GB | 4–6 tok/s | Tight / slow |
| Q8_0 | 28.6 GB | 3–5 tok/s | Won't fit |
| FP16 | 53.8 GB | 2–3 tok/s | Won't fit |
Open the full calculator →Everything a MacBook Pro M3 Pro (36GB) runsQwen3.6 27B on other machinesWhat to buy to run it →
Ran Qwen3.6 27B on a MacBook Pro M3 Pro (36GB)? Add your real numbers →