Can I run this LLM?
Can a NVIDIA H100 SXM (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 · 57.2 GB · 180–270 tok/s on a NVIDIA H100 SXM (80GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 45.3 GB | 199–298 tok/s | Runs great |
| Q3_K_M | 57.2 GB | 180–270 tok/s | Runs great |
| Q4_K_M | 73.0 GB | 160–240 tok/s | Won't fit |
| Q5_K_M | 83.5 GB | 149–224 tok/s | Won't fit |
| Q6_K | 99.0 GB | 135–203 tok/s | Won't fit |
| Q8_0 | 117.5 GB | 122–183 tok/s | Won't fit |
| FP16 | 221.0 GB | 78–118 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA H100 SXM (80GB) runsGLM-4.5 Air (MoE) on other machinesWhat to buy to run it →
Ran GLM-4.5 Air (MoE) on a NVIDIA H100 SXM (80GB)? Add your real numbers →