# zai-org/ChatGLM3

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

Repository: https://github.com/zai-org/ChatGLM3
Canonical: https://ross.abutalabs.com/products/chatglm3
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-01-13T06:55:26+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 1, release rhythm 35, longevity 74
- inputs: {"age_days": 1042, "days_push": 597, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 13655, forks 1580 (observed 2026-08-28T04:11:04.477135+00:00)

## What it is
ChatGLM3 is a series of open bilingual (Chinese-English) conversational large language models from Zhipu AI and Tsinghua University, including the 6B chat, base, and long-context (32K/128K) variants. The repository provides model weights, inference code, deployment tools, and demos for tool calling, code interpretation, and agent tasks.

## Use cases
- run a bilingual chat llm locally
- deploy an open-source chinese-english chatbot
- self-host a 6b parameter language model
- build an agent with function calling using an open llm
- process long documents with a 128k context model
- fine-tune an open dialogue model for research

## When to choose
- you need an open-weight bilingual Chinese/English chat model with permissive commercial terms after registration
- you want native tool calling and code interpreter support in an open LLM
- you need long-context variants up to 128K tokens
- you want low deployment barriers on consumer GPUs

## When to avoid
- you need the strongest general performance, since newer GLM-4 models supersede it
- you only want a hosted API without managing model weights
- you need a non-GPU or very low-resource deployment

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, chatbot, agent-framework, machine-learning
- domain: large-language-models, artificial-intelligence, chatbots
- platform: python, cross-platform
- tags: open-bilingual-llm, glm, chinese-english, function-call, code-interpreter, 6b-model, huggingface, natural-language-processing, gpu, linux

## Member repositories
- zai-org/ChatGLM3 (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:04.477135+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 2026-08-29T17:13:08.343690+00:00, confidence not recorded.
  - readme: https://github.com/zai-org/ChatGLM3 (fetched 2026-08-28T04:11:04.477135+00:00, sha f43d38d9eeec)
- Data as of 2026-08-30T08:39:29.467469+00:00.