Zhipu AI · 744B (40B active) · Mixture of Experts
MoE with 256 experts, 40B active — frontier-class agentic coding
155.9K downloads
2.1K likes
2026-02 128K context
Use Cases
chat reasoning code
Mixture of Experts
Total experts: 256
Active experts: 8
Active params: 40.0B
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 238.7 GB | low | — |
| Q3_K_M | 3 | 334 GB | moderate | — |
| Q4_K_M | 4 | 381.6 GB | good | — |
| Q5_K_M | 5 | 476.9 GB | good | — |
| Q6_K | 6 | 572.1 GB | excellent | — |
| Q8_0 | 8 | 762.7 GB | excellent | — |
| F16 | 16 | 1524.9 GB | lossless | — |
GPUs that run GLM-5
GLM-5 needs about 381.6 GB of VRAM at Q4_K_M — more than any single GPU we track. Running it takes multiple GPUs, a large unified-memory machine, or CPU offload with plenty of system RAM.
About this model
MoE with 256 experts, 40B active — frontier-class agentic coding