Can I run this LLM?
Can a MacBook Pro M3 Pro (18GB) run GLM-4.7 Flash (MoE)?
GLM · MIT · estimated for a 18.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: GLM-4.7 Flash (MoE) at Q2_K · 11.3 GB · 47–71 tok/s on a MacBook Pro M3 Pro (18GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 11.3 GB | 47–71 tok/s | Tight / slow |
| Q3_K_M | 14.6 GB | 41–61 tok/s | Won't fit |
| Q4_K_M | 18.3 GB | 36–53 tok/s | Won't fit |
| Q5_K_M | 21.4 GB | 32–48 tok/s | Won't fit |
| Q6_K | 24.7 GB | 29–44 tok/s | Won't fit |
| Q8_0 | 31.8 GB | 24–36 tok/s | Won't fit |
| FP16 | 59.9 GB | 14–22 tok/s | Won't fit |
Open the full calculator →Everything a MacBook Pro M3 Pro (18GB) runsGLM-4.7 Flash (MoE) on other machinesWhat to buy to run it →
Ran GLM-4.7 Flash (MoE) on a MacBook Pro M3 Pro (18GB)? Add your real numbers →