Can I run this LLM?
Can a Mac Studio M3 Ultra (512GB) run Granite 4.2 8B?
Granite · Apache 2.0 · estimated for a 512.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Granite 4.2 8B at FP16 · 17.6 GB · 26–39 tok/s on a Mac Studio M3 Ultra (512GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 3.4 GB | 76–114 tok/s | Runs great |
| Q3_K_M | 4.4 GB | 67–101 tok/s | Runs great |
| Q4_K_M | 5.4 GB | 60–90 tok/s | Runs great |
| Q5_K_M | 6.3 GB | 54–82 tok/s | Runs great |
| Q6_K | 7.2 GB | 50–75 tok/s | Runs great |
| Q8_0 | 9.4 GB | 42–63 tok/s | Runs great |
| FP16 | 17.6 GB | 26–39 tok/s | Runs great |
Open the full calculator →Everything a Mac Studio M3 Ultra (512GB) runsGranite 4.2 8B on other machinesWhat to buy to run it →
Ran Granite 4.2 8B on a Mac Studio M3 Ultra (512GB)? Add your real numbers →