--- title: "dolly vs ChatGLM-6B" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/databrickslabs-dolly-vs-zai-org-chatglm-6b" tools: ["databrickslabs-dolly", "zai-org-chatglm-6b"] --- # dolly vs ChatGLM-6B *GraphCanon updated Sep 20, 2026* ## Verdict Pick dolly if dolly is a large language model from Databricks, designed for both inference and training on the Databricks Machine Learning Platform. It is accessible via Hugging Face and requires specific GPU configurations for full-f; pick ChatGLM-6B if chatGLM-6B is an open-source bilingual dialogue language model with 6.2 billion parameters, optimized for Chinese and English conversations. It supports local. [dolly](https://www.databricks.com/blog/2023/03/24/hello-dolly-democratizing-magic-chatgpt-open-models.html) reports 11k GitHub stars, 1.1k forks, and 5 open issues, last pushed Jun 30, 2023. [ChatGLM-6B](https://github.com/zai-org/ChatGLM-6B) has 41k stars, 5.1k forks, and 605 open issues, last pushed Jun 27, 2024. Figures are from public GitHub metadata via [dolly's repository](https://github.com/databrickslabs/dolly) and [ChatGLM-6B's repository](https://github.com/zai-org/ChatGLM-6B). | | [dolly](/tools/databrickslabs-dolly.md) | [ChatGLM-6B](/tools/zai-org-chatglm-6b.md) | | --- | --- | --- | | Tagline | Databricks' Dolly, a large language model trained on the Databricks Machine Learning Platform | An Open Bilingual Dialogue Language Model | | Stars | 10,808 | 40,959 | | Forks | 1,134 | 5,101 | | Open issues | 5 | 605 | | Language | Python | Python | | Adopt for | Dolly is a large language model from Databricks, designed for both inference and training on the Databricks Machine Learning Platform. It is accessible via Hugging Face and requires specific GPU configurations for full-f | ChatGLM-6B is an open-source bilingual dialogue language model with 6.2 billion parameters, optimized for Chinese and English conversations. It supports local deployment with model quantization and offers efficient fine- | | Persona | - | - | | Runtime | - | - | | License | Dolly is licensed under the Apache-2.0 license, which is permissive and allows for free use, modification, and distribution of the software. | Apache-2.0 license, allowing for both academic and free commercial use after registration. | | Categories | Inference & Serving, LLM Frameworks | Inference & Serving, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [dolly](/tools/databrickslabs-dolly.md) | [ChatGLM-6B](/tools/zai-org-chatglm-6b.md) | | --- | --- | --- | | Days since push | 1175d | 813d | | Open issues (now) | 5 | 605 | | Stars delta | +3 (30d) | -53 (30d) | | Open issues delta | -1 (30d) | -2 (30d) | | Full report | [trust report](/tools/databrickslabs-dolly/trust.md) | [trust report](/tools/zai-org-chatglm-6b/trust.md) | ## Decision facts: dolly - **Requirements:** Requires A100 GPUs for optimal performance.; Integration with the Databricks Machine Learning Platform is necessary for full functionality. - **Adopt for:** Dolly is a large language model from Databricks, designed for both inference and training on the Databricks Machine Learning Platform. It is accessible via Hugging Face and requires specific GPU configurations for full-f - **License detail:** Dolly is licensed under the Apache-2.0 license, which is permissive and allows for free use, modification, and distribution of the software. ## Decision facts: ChatGLM-6B - **Pricing:** freemium - The model weights are completely open for academic research and allow free commercial use after registration. - **Requirements:** Min 8 GB RAM; Local deployment requires a minimum of 6GB of VRAM in INT4 quantization level for inference and 7GB for fine-tuning. - **Adopt for:** ChatGLM-6B is an open-source bilingual dialogue language model with 6.2 billion parameters, optimized for Chinese and English conversations. It supports local deployment with model quantization and offers efficient fine- - **License detail:** Apache-2.0 license, allowing for both academic and free commercial use after registration. ## Choose when ### Choose dolly if… - Requirements: Requires A100 GPUs for optimal performance.; Integration with the Databricks Machine Learning Platform is necessary for full functionality.. - Tags unique to dolly: chatbot, databricks, dolly, gpt. - When you need a language model that integrates seamlessly with the Databricks Machine Learning Platform for both training and inference. ### Choose ChatGLM-6B if… - Pricing: The model weights are completely open for academic research and allow free commercial use after registration.. - Requirements: Min 8 GB RAM; Local deployment requires a minimum of 6GB of VRAM in INT4 quantization level for inference and 7GB for fine-tuning.. - Tags unique to ChatGLM-6B: bilingual, commercial-use, dialogue, fine-tuning. - Use ChatGLM-6B when you need a model that is optimized for both Chinese and English conversations, offering a bilingual capability that is particularly strong in these languages. ## When NOT to use dolly - If your infrastructure does not support A100 GPUs or if you are unable to provision the required instance types in your region. - When you prefer not to use the Databricks Machine Learning Platform for your model training and inference needs. - If your project requires a model that is not licensed under Apache-2.0. ## When NOT to use ChatGLM-6B - Avoid using ChatGLM-6B if your project requires a model that supports languages other than Chinese and English, as it is specifically optimized for these two languages. - Do not use ChatGLM-6B if you need a model that is larger than 6.2 billion parameters, as it may not provide the depth of understanding or generation capabilities that larger models offer. ## Common questions ### What is the difference between dolly and ChatGLM-6B? dolly: Databricks' Dolly, a large language model trained on the Databricks Machine Learning Platform. ChatGLM-6B: An Open Bilingual Dialogue Language Model. See the comparison table for live GitHub stats and shared categories. ### When should I choose dolly over ChatGLM-6B? Choose dolly over ChatGLM-6B when Requirements: Requires A100 GPUs for optimal performance.; Integration with the Databricks Machine Learning Platform is necessary for full functionality.; Tags unique to dolly: chatbot, databricks, dolly, gpt; When you need a language model that integrates seamlessly with the Databricks Machine Learning Platform for both training and inference. ### When should I choose ChatGLM-6B over dolly? Choose ChatGLM-6B over dolly when Pricing: The model weights are completely open for academic research and allow free commercial use after registration.; Requirements: Min 8 GB RAM; Local deployment requires a minimum of 6GB of VRAM in INT4 quantization level for inference and 7GB for fine-tuning.; Tags unique to ChatGLM-6B: bilingual, commercial-use, dialogue, fine-tuning; Use ChatGLM-6B when you need a model that is optimized for both Chinese and English conversations, offering a bilingual capability that is particularly strong in these languages. ### When should I avoid dolly? If your infrastructure does not support A100 GPUs or if you are unable to provision the required instance types in your region. When you prefer not to use the Databricks Machine Learning Platform for your model training and inference needs. If your project requires a model that is not licensed under Apache-2.0. ### When should I avoid ChatGLM-6B? Avoid using ChatGLM-6B if your project requires a model that supports languages other than Chinese and English, as it is specifically optimized for these two languages. Do not use ChatGLM-6B if you need a model that is larger than 6.2 billion parameters, as it may not provide the depth of understanding or generation capabilities that larger models offer. ### Is dolly or ChatGLM-6B more popular on GitHub? ChatGLM-6B has more GitHub stars (40,959 vs 10,808). Stars measure visibility, not whether either tool fits your constraints. ### Are dolly and ChatGLM-6B open source? Yes - both are open-source projects on GitHub (dolly: Apache-2.0, ChatGLM-6B: Apache-2.0). ### Where can I find alternatives to dolly or ChatGLM-6B? GraphCanon lists graph-backed alternatives at [dolly alternatives](/tools/databrickslabs-dolly/alternatives) and [ChatGLM-6B alternatives](/tools/zai-org-chatglm-6b/alternatives) ([dolly markdown twin](/tools/databrickslabs-dolly/alternatives.md), [ChatGLM-6B markdown twin](/tools/zai-org-chatglm-6b/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/databrickslabs-dolly-vs-zai-org-chatglm-6b.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, dolly or ChatGLM-6B? dolly: Dormant. ChatGLM-6B: 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 dolly and ChatGLM-6B? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [dolly trust report](/tools/databrickslabs-dolly/trust); [ChatGLM-6B trust report](/tools/zai-org-chatglm-6b/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=databrickslabs-dolly`](/api/graphcanon/graph?tool=databrickslabs-dolly) - 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/_