Zhipu AI · 744B (40B active) · 專家混合（MoE）
MoE with 256 experts, 40B active — frontier-class agentic coding 看看你的 GPU 或 Mac 跑不跑得動 GLM-5——最低 415.7 GB，建議 692.9 GB。
2026-02128K context
專家混合（MoE）
專家總数： 256
啟用專家： 8
啟用参数： 40.0B
| 量化 | 位元 | VRAM | 品質 | 状態 |
|---|---|---|---|---|
| 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 | — |
Can I run GLM-5 locally?
- Can I run GLM-5 locally?
- GLM-5 needs about 415.7 GB of memory at a minimum and 692.9 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does GLM-5 need?
- At Q4_K_M, GLM-5 uses about 381.6 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.