Can I run this LLM?
Can a Mac Studio M3 Ultra (96GB) run Llama 3.1 8B?
Llama · Llama 3.1 Community · estimated for a 96.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Llama 3.1 8B at Q8_0 · 8.5 GB · 45–67 tok/s on a Mac Studio M3 Ultra (96GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 3.2 GB | 80–119 tok/s | Runs great |
| Q3_K_M | 4.0 GB | 71–107 tok/s | Runs great |
| Q4_K_M | 4.9 GB | 64–96 tok/s | Runs great |
| Q5_K_M | 5.7 GB | 58–87 tok/s | Runs great |
| Q6_K | 6.6 GB | 53–80 tok/s | Runs great |
| Q8_0 | 8.5 GB | 45–67 tok/s | Runs great |
Open the full calculator →Everything a Mac Studio M3 Ultra (96GB) runsLlama 3.1 8B on other machinesWhat to buy to run it →
Ran Llama 3.1 8B on a Mac Studio M3 Ultra (96GB)? Add your real numbers →