Can I run this LLM?
Can a Mac Studio M5 Ultra (256GB) run Qwen3.6 35B-A3B (MoE)?
Qwen · Apache 2.0 · estimated for a 256.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.6 35B-A3B (MoE) at FP16 · 69.4 GB · 76–114 tok/s on a Mac Studio M5 Ultra (256GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 12.3 GB | 139–208 tok/s | Runs great |
| Q3_K_M | 16.6 GB | 131–196 tok/s | Runs great |
| Q4_K_M | 22.1 GB | 121–182 tok/s | Runs great |
| Q5_K_M | 26.5 GB | 115–173 tok/s | Runs great |
| Q6_K | 29.3 GB | 111–167 tok/s | Runs great |
| Q8_0 | 36.9 GB | 102–153 tok/s | Runs great |
| FP16 | 69.4 GB | 76–114 tok/s | Runs great |
Open the full calculator →Everything a Mac Studio M5 Ultra (256GB) runsQwen3.6 35B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Qwen3.6 35B-A3B (MoE) on a Mac Studio M5 Ultra (256GB)? Add your real numbers →