Can I run this LLM?
Can a Desktop CPU, DDR5 dual-channel (32GB) run GLM-4.7 Flash (MoE)?
GLM · MIT · estimated for a 32.0 GB machine at 4K context.
Yes — it runs great.
Best fit: GLM-4.7 Flash (MoE) at Q3_K_M · 12.9 GB · 15–22 tok/s on a Desktop CPU, DDR5 dual-channel (32GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 9.7 GB | 17–26 tok/s | Runs great |
| Q3_K_M | 12.9 GB | 15–22 tok/s | Runs great |
| Q4_K_M | 18.2 GB | 12–18 tok/s | Tight / slow |
| Q5_K_M | 21.3 GB | 11–16 tok/s | Tight / slow |
| Q6_K | 24.7 GB | 10–14 tok/s | Won't fit |
| Q8_0 | 31.8 GB | 8–12 tok/s | Won't fit |
| FP16 | 59.9 GB | 5–7 tok/s | Won't fit |
Open the full calculator →Everything a Desktop CPU, DDR5 dual-channel (32GB) runsGLM-4.7 Flash (MoE) on other machinesWhat to buy to run it →
Ran GLM-4.7 Flash (MoE) on a Desktop CPU, DDR5 dual-channel (32GB)? Add your real numbers →