# zai-org/ChatGLM2-6B

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

Repository: https://github.com/zai-org/ChatGLM2-6B
Canonical: https://ross.abutalabs.com/products/chatglm2-6b
Language: Python
License: NOASSERTION
License Family: other
Topics: chatglm, chatglm-6b, large-language-models, llm
Last push: 2024-06-27T04:05:08+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 83
- inputs: {"age_days": 1166, "days_push": 797, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 15528, forks 1787 (observed 2026-08-28T04:11:09.991916+00:00)

## What it is
ChatGLM2-6B is an open-source bilingual (Chinese-English) 6B-parameter conversational large language model built on the GLM architecture. It provides model weights and inference code with efficient deployment options including INT4 quantization and 32K context support.

## Use cases
- run a self-hosted bilingual chatbot
- deploy a Chinese-English LLM on a single GPU
- fine-tune an open 6B chat model
- serve a chat LLM with low VRAM via INT4 quantization
- experiment with long-context dialogue models
- build a local assistant without API costs

## When to choose
- you need strong Chinese-language chat performance with an open model
- you have limited GPU memory and need quantized inference
- you want a permissively usable open-weight chat model for research or registered commercial use
- you need long-context dialogue up to 32K tokens

## When to avoid
- you need the newest capabilities like function calling or tool use (use GLM-4 instead)
- you require a permissive license without registration for commercial deployment
- you need a frontier-scale model for complex reasoning
- you want a maintained project with active development

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, chatbot, machine-learning, deep-learning
- domain: large-language-models, artificial-intelligence, chatbots
- platform: python, cross-platform
- tags: bilingual, chinese-english, open-weights, glm, quantization, 6b-parameters, self-hosted-llm, natural-language-processing, gpu, linux

## Member repositories
- zai-org/ChatGLM2-6B (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:09.991916+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:05:41.117253+00:00, confidence not recorded.
  - readme: https://github.com/zai-org/ChatGLM2-6B (fetched 2026-08-28T04:11:09.991916+00:00, sha 4b8aa0861af9)
- Data as of 2026-08-30T08:39:29.467469+00:00.