Can I run this LLM?
Can a NVIDIA H100 (80GB) run GLM-4.5 Air (MoE)?
GLM · MIT · estimated for a 80.0 GB machine at 4K context.
Yes — it runs great.
Best fit: GLM-4.5 Air (MoE) at Q3_K_M · 47.6 GB · 195–292 tok/s on a NVIDIA H100 (80GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 35.9 GB | 216–325 tok/s | Runs great |
| Q3_K_M | 47.6 GB | 195–292 tok/s | Runs great |
| Q4_K_M | 67.0 GB | 167–251 tok/s | Tight / slow |
| Q5_K_M | 78.7 GB | 154–231 tok/s | Won't fit |
| Q6_K | 91.1 GB | 142–213 tok/s | Won't fit |
| Q8_0 | 117.4 GB | 122–183 tok/s | Won't fit |
| FP16 | 220.9 GB | 78–118 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA H100 (80GB) runsGLM-4.5 Air (MoE) on other machinesWhat to buy to run it →
Ran GLM-4.5 Air (MoE) on a NVIDIA H100 (80GB)? Add your real numbers →