Can I run this LLM?
Can a Mac Studio M1 Ultra (128GB) run Llama 3.3 70B Instruct?
Llama · Llama 3.3 Community · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Llama 3.3 70B Instruct at Q3_K_M · 34.3 GB · 14–21 tok/s on a Mac Studio M1 Ultra (128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 26.4 GB | 17–26 tok/s | Runs great |
| Q3_K_M | 34.3 GB | 14–21 tok/s | Runs great |
| Q4_K_M | 42.5 GB | 11–17 tok/s | Tight / slow |
| Q5_K_M | 50.0 GB | 10–15 tok/s | Tight / slow |
| Q6_K | 57.9 GB | 9–13 tok/s | Tight / slow |
| Q8_0 | 75.0 GB | 7–10 tok/s | Tight / slow |
| FP16 | 141.1 GB | 4–6 tok/s | Won't fit |
Open the full calculator →Everything a Mac Studio M1 Ultra (128GB) runsLlama 3.3 70B Instruct on other machinesWhat to buy to run it →
Ran Llama 3.3 70B Instruct on a Mac Studio M1 Ultra (128GB)? Add your real numbers →