Can I run this LLM?
Can a Mac Studio M3 Ultra (96GB) run Qwen3.5 4B?
Qwen · Apache 2.0 · estimated for a 96.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.5 4B at FP16 · 8.4 GB · 45–68 tok/s on a Mac Studio M3 Ultra (96GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 2.3 GB | 91–137 tok/s | Runs great |
| Q4_K_M | 2.7 GB | 85–128 tok/s | Runs great |
| Q5_K_M | 3.1 GB | 80–120 tok/s | Runs great |
| Q6_K | 3.5 GB | 76–114 tok/s | Runs great |
| Q8_0 | 4.5 GB | 67–101 tok/s | Runs great |
| FP16 | 8.4 GB | 45–68 tok/s | Runs great |
Open the full calculator →Everything a Mac Studio M3 Ultra (96GB) runsQwen3.5 4B on other machinesWhat to buy to run it →
Ran Qwen3.5 4B on a Mac Studio M3 Ultra (96GB)? Add your real numbers →