Can I run this LLM?
Can a NVIDIA RTX 5080 (16GB) run GLM-4.7 Flash (MoE)?
GLM · MIT · estimated for a 16.0 GB machine at 4K context.
Yes — it runs great.
Best fit: GLM-4.7 Flash (MoE) at Q2_K · 11.3 GB · 203–305 tok/s on a NVIDIA RTX 5080 (16GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 11.3 GB | 203–305 tok/s | Runs great |
| Q3_K_M | 14.6 GB | 186–279 tok/s | Won't fit |
| Q4_K_M | 18.3 GB | 169–254 tok/s | Won't fit |
| Q5_K_M | 21.4 GB | 158–237 tok/s | Won't fit |
| Q6_K | 24.7 GB | 147–220 tok/s | Won't fit |
| Q8_0 | 31.8 GB | 128–192 tok/s | Won't fit |
| FP16 | 59.9 GB | 85–127 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 5080 (16GB) runsGLM-4.7 Flash (MoE) on other machinesWhat to buy to run it →
Ran GLM-4.7 Flash (MoE) on a NVIDIA RTX 5080 (16GB)? Add your real numbers →