Can I run this LLM?
Can a MacBook Air/Pro M2 (16GB) run DeepSeek-R1-Distill 8B?
DeepSeek · Llama 3.1 Community · estimated for a 16.0 GB machine at 4K context.
Yes — it runs great.
Best fit: DeepSeek-R1-Distill 8B at Q3_K_M · 4.0 GB · 14–20 tok/s on a MacBook Air/Pro M2 (16GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 3.2 GB | 16–25 tok/s | Runs great |
| Q3_K_M | 4.0 GB | 14–20 tok/s | Runs great |
| Q4_K_M | 4.9 GB | 12–17 tok/s | Tight / slow |
| Q5_K_M | 5.7 GB | 10–15 tok/s | Tight / slow |
| Q6_K | 6.6 GB | 9–13 tok/s | Tight / slow |
| Q8_0 | 8.5 GB | 7–11 tok/s | Tight / slow |
| FP16 | 16.1 GB | 4–6 tok/s | Won't fit |
Open the full calculator →Everything a MacBook Air/Pro M2 (16GB) runsDeepSeek-R1-Distill 8B on other machinesWhat to buy to run it →
Ran DeepSeek-R1-Distill 8B on a MacBook Air/Pro M2 (16GB)? Add your real numbers →