--- title: "ChatGLM2-6B vs GLM-130B" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/zai-org-chatglm2-6b-vs-zai-org-glm-130b" tools: ["zai-org-chatglm2-6b", "zai-org-glm-130b"] --- # ChatGLM2-6B vs GLM-130B *GraphCanon updated Aug 1, 2026* ## Verdict Pick ChatGLM2-6B if open bilingual dialogue model with enhanced performance, longer context length up to 32K tokens, and efficient inference; pick GLM-130B if gLM-130B specializes in bilingual capabilities and is open source under the Apache-2.0 license. [ChatGLM2-6B](https://github.com/zai-org/ChatGLM2-6B) reports 16k GitHub stars, 1.8k forks, and 450 open issues, last pushed Jun 27, 2024. [GLM-130B](https://github.com/zai-org/GLM-130B) has 7.7k stars, 600 forks, and 124 open issues, last pushed Jul 25, 2023. Figures are from public GitHub metadata via [ChatGLM2-6B's repository](https://github.com/zai-org/ChatGLM2-6B) and [GLM-130B's repository](https://github.com/zai-org/GLM-130B). | | [ChatGLM2-6B](/tools/zai-org-chatglm2-6b.md) | [GLM-130B](/tools/zai-org-glm-130b.md) | | --- | --- | --- | | Tagline | An Open Bilingual Chat LLM | GLM-130B: An Open Bilingual Pre-Trained Model | | Stars | 15,540 | 7,656 | | Forks | 1,794 | 600 | | Open issues | 450 | 124 | | Language | Python | Python | | Adopt for | Open bilingual dialogue model with enhanced performance, longer context length up to 32K tokens, and efficient inference. | GLM-130B specializes in bilingual capabilities and is open source under the Apache-2.0 license. | | Persona | - | - | | Runtime | - | - | | License | Other | The GLM-130B codebase and framework are available under the permissive Apache-2.0 license; however, usage of model weights is governed by its own Model License. | | Categories | LLM Frameworks | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [ChatGLM2-6B](/tools/zai-org-chatglm2-6b.md) | [GLM-130B](/tools/zai-org-glm-130b.md) | | --- | --- | --- | | Days since push | 765d | 1103d | | Open issues (now) | 450 | 124 | | Full report | [trust report](/tools/zai-org-chatglm2-6b/trust.md) | [trust report](/tools/zai-org-glm-130b/trust.md) | ## Decision facts: ChatGLM2-6B - **Adopt for:** Open bilingual dialogue model with enhanced performance, longer context length up to 32K tokens, and efficient inference. ## Decision facts: GLM-130B - **Pricing:** freemium - Free to use with specific licensing requirements for model weights. - **Requirements:** Min 8 GB RAM - **Adopt for:** GLM-130B specializes in bilingual capabilities and is open source under the Apache-2.0 license. - **License detail:** The GLM-130B codebase and framework are available under the permissive Apache-2.0 license; however, usage of model weights is governed by its own Model License. ## Choose when ### Choose ChatGLM2-6B if… - License: ChatGLM2-6B is Other, GLM-130B is Apache-2.0. - Tags unique to ChatGLM2-6B: chatglm, chatglm-6b, large language models, llm. - For applications needing bilingual support with improved accuracy in MMLU, CEval, GSM8K, BBH datasets. ### Choose GLM-130B if… - License: GLM-130B is Apache-2.0, ChatGLM2-6B is Other. - Pricing: Free to use with specific licensing requirements for model weights.. - Requirements: Min 8 GB RAM. - Tags unique to GLM-130B: bilingual, iclr 2023, language-model, pre-trained. - Also covers Model Training. - Use GLM-130B when you need strong support for two languages to facilitate multilingual content creation or processing, given its specialized training in bilingual contexts. ## When NOT to use ChatGLM2-6B - Avoid if the use case does not benefit from bilingual capabilities. - Not suitable for applications that need more than free tier commercial usage without registration through provided survey. ## When NOT to use GLM-130B - Avoid GLM-130B if your application demands single-language proficiency exclusively, as its strength lies specifically in bilingual support. - Do not use this model if you seek a resource with multilingual capabilities beyond two specific languages, since it focuses particularly on only a dual-language environment. ## Common questions ### What is the difference between ChatGLM2-6B and GLM-130B? ChatGLM2-6B: An Open Bilingual Chat LLM. GLM-130B: GLM-130B: An Open Bilingual Pre-Trained Model. See the comparison table for live GitHub stats and shared categories. ### When should I choose ChatGLM2-6B over GLM-130B? Choose ChatGLM2-6B over GLM-130B when License: ChatGLM2-6B is Other, GLM-130B is Apache-2.0; Tags unique to ChatGLM2-6B: chatglm, chatglm-6b, large language models, llm; For applications needing bilingual support with improved accuracy in MMLU, CEval, GSM8K, BBH datasets. ### When should I choose GLM-130B over ChatGLM2-6B? Choose GLM-130B over ChatGLM2-6B when License: GLM-130B is Apache-2.0, ChatGLM2-6B is Other; Pricing: Free to use with specific licensing requirements for model weights.; Requirements: Min 8 GB RAM; Tags unique to GLM-130B: bilingual, iclr 2023, language-model, pre-trained; Also covers Model Training; Use GLM-130B when you need strong support for two languages to facilitate multilingual content creation or processing, given its specialized training in bilingual contexts. ### When should I avoid ChatGLM2-6B? Avoid if the use case does not benefit from bilingual capabilities. Not suitable for applications that need more than free tier commercial usage without registration through provided survey. ### When should I avoid GLM-130B? Avoid GLM-130B if your application demands single-language proficiency exclusively, as its strength lies specifically in bilingual support. Do not use this model if you seek a resource with multilingual capabilities beyond two specific languages, since it focuses particularly on only a dual-language environment. ### Is ChatGLM2-6B or GLM-130B more popular on GitHub? ChatGLM2-6B has more GitHub stars (15,540 vs 7,656). Stars measure visibility, not whether either tool fits your constraints. ### Are ChatGLM2-6B and GLM-130B open source? Yes - both are open-source projects on GitHub (ChatGLM2-6B: Other, GLM-130B: Apache-2.0). ### Where can I find alternatives to ChatGLM2-6B or GLM-130B? GraphCanon lists graph-backed alternatives at [ChatGLM2-6B alternatives](/tools/zai-org-chatglm2-6b/alternatives) and [GLM-130B alternatives](/tools/zai-org-glm-130b/alternatives) ([ChatGLM2-6B markdown twin](/tools/zai-org-chatglm2-6b/alternatives.md), [GLM-130B markdown twin](/tools/zai-org-glm-130b/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/zai-org-chatglm2-6b-vs-zai-org-glm-130b.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, ChatGLM2-6B or GLM-130B? ChatGLM2-6B: Dormant. GLM-130B: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for ChatGLM2-6B and GLM-130B? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [ChatGLM2-6B trust report](/tools/zai-org-chatglm2-6b/trust); [GLM-130B trust report](/tools/zai-org-glm-130b/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=zai-org-chatglm2-6b`](/api/graphcanon/graph?tool=zai-org-chatglm2-6b) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_