ChatGLM Models by Tsinghua Knowledge Engineering Group (THUDM)
This model family is considered obsolete. Consider newer alternatives in Related Model Families below.
1 model2023Up to 2k ctx
About
The original ChatGLM family of open-source bilingual (Chinese-English) chat models from THUDM (Tsinghua University KEG Lab and Zhipu AI). Pre-trained on approximately 1 trillion Chinese-English tokens with RLHF alignment, the ChatGLM-6B model achieved strong bilingual performance at the 6B parameter scale and became a widely-used baseline in Chinese-language LLM research. Superseded by ChatGLM2 in June 2023.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
ChatGLM-6BCurrent
Use when the workload needs 2k context and 6.2B parameters.
2023-032k context6.2B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| ChatGLM-6B | Use when the workload needs 2k context and 6.2B parameters. | 2023-03 | 2k context6.2B parameters | Current |
Release Timeline
1 release group2023-03
1 current
ChatGLM-6B
Current2k context6.2B parameters
Specifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| ChatGLM-6B | 2023-03 | 2k | 6.2B |
Frequently Asked Questions
- What is ChatGLM used for?
- The original ChatGLM family of open-source bilingual (Chinese-English) chat models from THUDM (Tsinghua University KEG Lab and Zhipu AI).
- How does ChatGLM compare to ChatGLM-4?
- ChatGLM by Tsinghua Knowledge Engineering Group (THUDM) is strongest where you need its listed use cases, while ChatGLM-4 by Tsinghua Knowledge Engineering Group (THUDM) is the closest related family to check for adjacent model selection. ChatGLM has 1 listed variant and reaches up to 2k context, while ChatGLM-4 reaches up to 128k context, so compare the specs and pricing tables before choosing a production model.
- Which ChatGLM model should I use?
- If price is the main constraint, use the pricing table first because ChatGLM does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate ChatGLM-6B with 2k context.
