# zai-org/ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

Repository: https://github.com/zai-org/ChatGLM-6B
Canonical: https://ross.abutalabs.com/products/chatglm-6b
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-06-27T04:05:25+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 90
- inputs: {"age_days": 1269, "days_push": 797, "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 40983, forks 5109 (observed 2026-08-28T04:12:08.399873+00:00)

## What it is
ChatGLM-6B is an open-source bilingual (Chinese-English) 6.2B-parameter dialogue language model based on the GLM architecture, optimized for Chinese question answering and conversation. It supports INT4 quantization for local deployment on consumer GPUs (as low as 6GB VRAM) and efficient fine-tuning via P-Tuning v2.

## Use cases
- run a chatbot locally on a consumer GPU
- deploy a bilingual Chinese-English dialogue model
- fine-tune an LLM for Chinese question answering
- quantize a 6B language model to fit 6GB VRAM
- build a self-hosted ChatGPT-like assistant
- adapt an open dialogue model to a custom domain

## When to choose
- you need a self-hosted bilingual dialogue model with low VRAM requirements
- your primary use case involves Chinese-language conversation
- you want to fine-tune an open LLM with P-Tuning v2 on limited hardware

## When to avoid
- you need state-of-the-art performance, since newer GLM-4 models supersede it
- you require long-context or function-calling features out of the box
- you need guaranteed output accuracy for safety-critical services

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, chatbot, machine-learning, rag
- domain: large-language-models, artificial-intelligence, chatbots
- platform: python, windows
- tags: bilingual, chinese-english, glm, quantization, local-deployment, fine-tuning, p-tuning, open-weights, natural-language-processing, gpu, linux, macos

## Member repositories
- zai-org/ChatGLM-6B (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:08.399873+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 2026-08-29T16:23:16.411926+00:00, confidence not recorded.
  - readme: https://github.com/zai-org/ChatGLM-6B (fetched 2026-08-28T04:12:08.399873+00:00, sha 5d0a2995f6ef)
- Data as of 2026-08-30T08:39:29.467469+00:00.