Can I run this LLM?
Can a NVIDIA RTX 5090 (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 Q6_K · 24.7 GB · 204–305 tok/s on a NVIDIA RTX 5090 (32GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 11.3 GB | 256–385 tok/s | Runs great |
| Q3_K_M | 14.6 GB | 241–362 tok/s | Runs great |
| Q4_K_M | 18.3 GB | 226–339 tok/s | Runs great |
| Q5_K_M | 21.4 GB | 214–322 tok/s | Runs great |
| Q6_K | 24.7 GB | 204–305 tok/s | Runs great |
| Q8_0 | 31.8 GB | 183–275 tok/s | Won't fit |
| FP16 | 59.9 GB | 132–198 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 5090 (32GB) runsGLM-4.7 Flash (MoE) on other machinesWhat to buy to run it →
Ran GLM-4.7 Flash (MoE) on a NVIDIA RTX 5090 (32GB)? Add your real numbers →