
Z.ai released GLM 5.1 on April 3, 2026. The registry currently records it as open weights.
Model publication
zai-org
GLM 5.1Open the source for GLM 5.1
GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete, engineering-grade results.
- Licence
- mit
- Architecture
- GlmMoeDsaForCausalLM
- Parameters
- 754B
- Context
- 204.8K tokens
- Artifact format
- safetensors
- Quantization
- native BF16
- Download size
- 1.4 TB

Hardware to run it (inference, estimated)
1.6 TB VRAM minimum · 2.1 TB recommended · 2.1 TB system RAM · 1.4 TB storage
Estimated from parameter count and stored precision; verify against the selected runtime and context length.
Benchmarks
No benchmark observation recorded for this model.