back

GLM-5.1

MIT

Zhipu AI · 754B (40B active) · Mixture of Experts

Improved agentic coding — SOTA SWE-bench Pro, long-horizon tasks

0 downloads 0 likes 2026-04 128K context

Use Cases

chat reasoning code

Mixture of Experts

Total experts: 256
Active experts: 8
Active params: 40.0B

Quantization Options

Quant Bits VRAM Quality Status
Q2_K 2 241.9 GB low
Q3_K_M 3 338.4 GB moderate
Q4_K_M 4 386.7 GB good
Q5_K_M 5 483.3 GB good
Q6_K 6 579.8 GB excellent
Q8_0 8 772.9 GB excellent
F16 16 1545.4 GB lossless