Can I run this LLM?
Can a MacBook Pro M5 Max (128GB) run Kimi Linear 48B-A3B (MoE)?
Kimi · MIT · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Kimi Linear 48B-A3B (MoE) at Q8_0 · 52.3 GB · 73–110 tok/s on a MacBook Pro M5 Max (128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 17.5 GB | 118–176 tok/s | Runs great |
| Q3_K_M | 22.7 GB | 108–162 tok/s | Runs great |
| Q4_K_M | 30.1 GB | 97–145 tok/s | Runs great |
| Q5_K_M | 35.1 GB | 90–135 tok/s | Runs great |
| Q6_K | 40.5 GB | 84–126 tok/s | Runs great |
| Q8_0 | 52.3 GB | 73–110 tok/s | Runs great |
| FP16 | 98.3 GB | 49–74 tok/s | Won't fit |
Open the full calculator →Everything a MacBook Pro M5 Max (128GB) runsKimi Linear 48B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Kimi Linear 48B-A3B (MoE) on a MacBook Pro M5 Max (128GB)? Add your real numbers →