Can I run this LLM?
Can a NVIDIA RTX 4090 (24GB) run GLM-4.7 Flash (MoE)?
GLM · MIT · estimated for a 24.0 GB machine at 4K context.
Yes — it runs great.
Best fit: GLM-4.7 Flash (MoE) at Q3_K_M · 14.6 GB · 190–285 tok/s on a NVIDIA RTX 4090 (24GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 11.3 GB | 208–312 tok/s | Runs great |
| Q3_K_M | 14.6 GB | 190–285 tok/s | Runs great |
| Q4_K_M | 18.3 GB | 174–261 tok/s | Tight / slow |
| Q5_K_M | 21.4 GB | 162–243 tok/s | Won't fit |
| Q6_K | 24.7 GB | 151–227 tok/s | Won't fit |
| Q8_0 | 31.8 GB | 132–198 tok/s | Won't fit |
| FP16 | 59.9 GB | 88–132 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 4090 (24GB) runsGLM-4.7 Flash (MoE) on other machinesWhat to buy to run it →
Ran GLM-4.7 Flash (MoE) on a NVIDIA RTX 4090 (24GB)? Add your real numbers →