ChatGLM3-6B
Bilingual Chinese-English 6B dialogue model with native function calling and code execution; open weights.
Retired
ChatGLM3-6B appears to be discontinued or shut down — legacy checkpoint; Zhipu moved to GLM-4/GLM-5 line This page is kept as an archive record and is excluded from search engines.
About
ChatGLM3-6B is the third-generation open dialogue model jointly released by Zhipu AI and Tsinghua University's KEG lab on October 27, 2023. The 6B base model uses a bilingual Chinese-English design and was positioned as the strongest sub-10B base model of its time across reasoning, math, code, and general-knowledge benchmarks. Its signature advance was baking agent-style capabilities into the default open-model interface: native function calling, a code interpreter, and a newly designed prompt format supporting multi-turn dialogue. Zhipu also open-sourced a 32K long-context variant alongside the standard 8K model.
Limitations: ChatGLM3 is now a legacy checkpoint — Zhipu has moved through GLM-4 to the MIT-licensed GLM-5 line (and rebranded as Z.ai), so it is mainly useful where its small size and low hosting cost matter more than frontier capability. Licensing needs care: the weights are fully open for academic research, but commercial use requires registration through Zhipu's questionnaire rather than a standard OSI license, so verify current terms before shipping a product on it.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 6/10
Scored 6/10 (metrics tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 68; Trending score 58/100 from researcher assessment.