Can I run this LLM?
Can a NVIDIA H200 (141GB) run GLM-5.3 Flash (MoE)?
GLM · MIT · estimated for a 141.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: GLM-5.3 Flash (MoE) at Q2_K · 125.7 GB · 211–316 tok/s on a NVIDIA H200 (141GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 125.7 GB | 211–316 tok/s | Tight / slow |
| Q3_K_M | 155.0 GB | 192–288 tok/s | Won't fit |
| Q4_K_M | 200.8 GB | 169–253 tok/s | Won't fit |
| Q5_K_M | 243.7 GB | 151–227 tok/s | Won't fit |
| Q6_K | 281.0 GB | 139–208 tok/s | Won't fit |
| Q8_0 | 341.5 GB | 123–184 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA H200 (141GB) runsGLM-5.3 Flash (MoE) on other machinesWhat to buy to run it →
Ran GLM-5.3 Flash (MoE) on a NVIDIA H200 (141GB)? Add your real numbers →