Overview
Description
GLM-5 is a flagship open-weights foundation model developed by Zhipu AI and THUDM for advanced reasoning, code synthesis, and long-horizon agent workflows. Released under the MIT license, it delivers frontier performance on benchmark suites like SWE-bench and GPQA Diamond with extensive context processing and multi-step tool execution.
Technical scorecard
License
MIT
Commercial use
Yes
OpenAI-compatible API
Yes
REST API
Yes
Fine-tuning support
Yes
Quantization support
safetensors, GGUF
Docker available
No
GUI / no-code available
No
Telemetry
None
Offline after setup
Yes
Data & Privacy
Does it send data online?
After setup, this listing is marked as usable offline. Confirm network behavior against the upstream project before regulated deployment.
Does it store history?
Not verified in this directory yet. Review the upstream docs for persistence, logs, and workspace storage.
License checks?
Commercial use is marked as allowed or likely allowed by the listed license.
Telemetry?
None
Last verified: Aug 24, 2026. Maintainer verification should be treated as directory guidance, not legal advice.
Planning to deploy GLM-5?
Estimate exact GPU VRAM requirements, context limits, fine-tuning memory, and infrastructure costs for GLM-5 before committing to hardware.
Calculate Hardware & GPU Sizing →Setup & Installation
A developer can usually get this running with standard docs.
# Start with the official project repository
# https://github.com/THUDM/GLM-4Hardware Requirements
Works Well With