Can I run this LLM?
Can a MacBook Pro M1 Pro (32GB) run Qwen3.8 27B?
Qwen · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: Qwen3.8 27B at Q2_K · 10.8 GB · 11–17 tok/s on a MacBook Pro M1 Pro (32GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 10.8 GB | 11–17 tok/s | Tight / slow |
| Q3_K_M | 13.4 GB | 9–14 tok/s | Tight / slow |
| Q4_K_M | 17.4 GB | 7–11 tok/s | Tight / slow |
| Q5_K_M | 20.9 GB | 6–9 tok/s | Tight / slow |
| Q6_K | 23.9 GB | 5–8 tok/s | Won't fit |
| Q8_0 | 29.1 GB | 4–7 tok/s | Won't fit |
| FP16 | 54.7 GB | 2–4 tok/s | Won't fit |
Open the full calculator →Everything a MacBook Pro M1 Pro (32GB) runsQwen3.8 27B on other machinesWhat to buy to run it →
Ran Qwen3.8 27B on a MacBook Pro M1 Pro (32GB)? Add your real numbers →