Can I run this LLM?
Can a MacBook Pro M4 Pro (24GB) run Qwen3.6 35B-A3B (MoE)?
Qwen · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: Qwen3.6 35B-A3B (MoE) at Q3_K_M · 14.9 GB · 68–102 tok/s on a MacBook Pro M4 Pro (24GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 14.9 GB | 68–102 tok/s | Tight / slow |
| Q4_K_M | 21.0 GB | 57–86 tok/s | Won't fit |
| Q5_K_M | 24.7 GB | 52–78 tok/s | Won't fit |
| Q6_K | 28.6 GB | 47–71 tok/s | Won't fit |
| Q8_0 | 36.8 GB | 40–60 tok/s | Won't fit |
| FP16 | 69.3 GB | 25–37 tok/s | Won't fit |
Open the full calculator →Everything a MacBook Pro M4 Pro (24GB) runsQwen3.6 35B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Qwen3.6 35B-A3B (MoE) on a MacBook Pro M4 Pro (24GB)? Add your real numbers →