GLM 5
MoEGLM
Zhipu's 744B frontier MoE. $1.0/M tokens via API. Cluster-scale deployment only; expect 200GB+ VRAM even at aggressive quantization.
Provider
Zhipu AI
Parameters
744B
Context
128K
Released
2026-04-08
VRAM Requirements by Quantization
| Method | Disk Size | VRAM Required | Fits GPUs |
|---|---|---|---|
| Q4_K_M | 370 GB | 400 GB | 0 GPUs |
| Q2_K | 195 GB | 215 GB | 0 GPUs |
Benchmark Scores
mmlu87%
humaneval89.5%
Scores are approximate and may vary by quantization level.
HuggingFace
zai-org/GLM-5