Can I run this LLM?
Can a MacBook Pro M4 Pro (48GB) run DeepSeek-R1-Distill 8B?
DeepSeek · Llama 3.1 Community · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: DeepSeek-R1-Distill 8B at Q8_0 · 8.5 GB · 18–27 tok/s on a MacBook Pro M4 Pro (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 3.2 GB | 38–58 tok/s | Runs great |
| Q3_K_M | 4.0 GB | 33–49 tok/s | Runs great |
| Q4_K_M | 4.9 GB | 28–42 tok/s | Runs great |
| Q5_K_M | 5.7 GB | 25–38 tok/s | Runs great |
| Q6_K | 6.6 GB | 22–34 tok/s | Runs great |
| Q8_0 | 8.5 GB | 18–27 tok/s | Runs great |
| FP16 | 16.1 GB | 10–16 tok/s | Tight / slow |
Open the full calculator →Everything a MacBook Pro M4 Pro (48GB) runsDeepSeek-R1-Distill 8B on other machinesWhat to buy to run it →
Ran DeepSeek-R1-Distill 8B on a MacBook Pro M4 Pro (48GB)? Add your real numbers →