GLM 4.7 Flash
A
AI Socratic
Z.ai released GLM 4.7 Flash on January 19, 2026. The registry currently records it as open weights.
Model publication
zai-org
GLM 4.7 FlashOpen the source for GLM 4.7 Flash
Open weights
As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.
- Licence
- mit
- Architecture
- Glm4MoeLiteForCausalLM
- Parameters
- 31.2B
- Context
- 202.8K tokens
- Artifact format
- safetensors
- Quantization
- native BF16
- Download size
- 59 GB
Hardware to run it (inference, estimated)
70 GB VRAM minimum · 88 GB recommended · 88 GB system RAM · 59 GB storage
Estimated from parameter count and stored precision; verify against the selected runtime and context length.
Benchmarks
No benchmark observation recorded for this model.
About the Authors
A