ChatGLM-6B
Small bilingual Chinese-English chat model that runs on a consumer GPU; one of China's earliest widely used open LLMs.
A 6B chat model derived from the GLM-130B line, tuned for dialogue and runnable on consumer GPUs with INT4 quantization. It preceded Llama 2 (2023-07) and drew heavy community use; weights were free for research, with commercial use after registration.
- Date
- Tuesday, 14 March 2023
- Lab
- Zhipu AI / Z.ai
- Kind
- open-weights
- Access
- open weights (restricted license)
Figures
| Measure | Value | Measured by |
|---|---|---|
| GitHub stars (repo THUDM/ChatGLM-6B) | 40.9k snapshot read 2026-10 | independent |
GitHub repo created 2023-03-13 UTC (2023-03-14 Beijing); release day taken from the repo and widely cited reports, not from a dated Zhipu post I could open. License terms (registration for commercial use) are from the ChatGLM3 repo, same family.
Sources
This record was checked against its sources on 6 October 2026. How we check