Can I run this LLM?
Can a Mac Studio M5 Ultra (96GB) run Qwen3 32B?
Qwen · Apache 2.0 · estimated for a 96.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3 32B at Q8_0 · 34.8 GB · 20–31 tok/s on a Mac Studio M5 Ultra (96GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 12.3 GB | 45–68 tok/s | Runs great |
| Q3_K_M | 16.0 GB | 38–57 tok/s | Runs great |
| Q4_K_M | 19.8 GB | 32–48 tok/s | Runs great |
| Q5_K_M | 23.2 GB | 28–43 tok/s | Runs great |
| Q6_K | 26.9 GB | 25–38 tok/s | Runs great |
| Q8_0 | 34.8 GB | 20–31 tok/s | Runs great |
| FP16 | 65.5 GB | 12–17 tok/s | Won't fit |
Open the full calculator →Everything a Mac Studio M5 Ultra (96GB) runsQwen3 32B on other machinesWhat to buy to run it →
Ran Qwen3 32B on a Mac Studio M5 Ultra (96GB)? Add your real numbers →