--- title: "model_search vs FastChat" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/google-model-search-vs-lm-sys-fastchat" tools: ["google-model-search", "lm-sys-fastchat"] --- # model_search vs FastChat *GraphCanon updated Jul 11, 2026* ## Verdict Pick model_search when tags unique to model_search: python; pick FastChat when tags unique to FastChat: evaluation system, large-language-models, chatbots, distributed serving. [model_search](https://github.com/google/model_search) reports 3.2k GitHub stars, 549 forks, and 53 open issues, last pushed Jul 30, 2024. [FastChat](https://github.com/lm-sys/FastChat) has 39k stars, 4.8k forks, and 1.0k open issues, last pushed May 1, 2026. Figures are from public GitHub metadata via [model_search's repository](https://github.com/google/model_search) and [FastChat's repository](https://github.com/lm-sys/FastChat). | | [model_search](/tools/google-model-search.md) | [FastChat](/tools/lm-sys-fastchat.md) | | --- | --- | --- | | Tagline | model_search | An open platform for training, serving, and evaluating large language models | | Stars | 3,241 | 39,490 | | Forks | 549 | 4,788 | | Open issues | 53 | 1,027 | | Language | Python | Python | | Adopt for | - | FastChat is a comprehensive open platform for managing large language models (LLMs) that includes capabilities for training, serving, evaluating, and comparing chatbot models via web UIs and RESTful APIs. It powers ChatB | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Apache-2.0 | | Categories | Model Training, Evaluation & Observability | Model Training, LLM Frameworks, Inference & Serving, Evaluation & Observability | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [model_search](/tools/google-model-search.md) | [FastChat](/tools/lm-sys-fastchat.md) | | --- | --- | --- | | Maintenance | Archived (8%) | Steady (60%) | | Days since push | 711d | 71d | | Archived on GitHub | Yes | No | | Open issues (now) | 53 | 1.0k | | Security scan | 268 low (268 low) | No lockfile | | Full report | [trust report](/tools/google-model-search/trust.md) | [trust report](/tools/lm-sys-fastchat/trust.md) | ## Shared compatibility - **Python**: [model_search](/tools/google-model-search.md) - Python runtime; [FastChat](/tools/lm-sys-fastchat.md) - Python runtime ## Decision facts: FastChat - **Adopt for:** FastChat is a comprehensive open platform for managing large language models (LLMs) that includes capabilities for training, serving, evaluating, and comparing chatbot models via web UIs and RESTful APIs. It powers ChatB ## Choose when ### Choose model_search if… - Tags unique to model_search: python. - Leaner open-issue backlog (53). ### Choose FastChat if… - Tags unique to FastChat: evaluation system, large-language-models, chatbots, distributed serving. - Also covers LLM Frameworks, Inference & Serving. - - You are looking to train and evaluate state-of-the-art models such as Vicuna or MT-Bench. ## When NOT to use model_search - model_search is archived on GitHub. Prefer an active alternative unless you maintain a private fork or need a frozen dependency. - Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. - Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. ## When NOT to use FastChat - - You require a proprietary or closed-source framework; FastChat is open-source under Apache-2.0 license and its use might be unsuitable for environments requiring proprietary solutions. - - Your chatbot evaluation needs do not align with the types of data used in FastChat's datasets (e.g., human votes, MT-Bench evaluations). - - You prefer a more user-friendly setup without the need to clone a repository and manually install dependencies; FastChat requires installation from source with additional steps for Rust and CMake on - + Mac. ## Common questions ### What is the difference between model_search and FastChat? model_search: model_search. FastChat: An open platform for training, serving, and evaluating large language models. See the comparison table for live GitHub stats and shared categories. ### When should I choose model_search over FastChat? Choose model_search over FastChat when Tags unique to model_search: python; Leaner open-issue backlog (53). ### When should I choose FastChat over model_search? Choose FastChat over model_search when Tags unique to FastChat: evaluation system, large-language-models, chatbots, distributed serving; Also covers LLM Frameworks, Inference & Serving; - You are looking to train and evaluate state-of-the-art models such as Vicuna or MT-Bench. ### When should I avoid model_search? model_search is archived on GitHub. Prefer an active alternative unless you maintain a private fork or need a frozen dependency. Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. ### When should I avoid FastChat? - You require a proprietary or closed-source framework; FastChat is open-source under Apache-2.0 license and its use might be unsuitable for environments requiring proprietary solutions. - Your chatbot evaluation needs do not align with the types of data used in FastChat's datasets (e.g., human votes, MT-Bench evaluations). - You prefer a more user-friendly setup without the need to clone a repository and manually install dependencies; FastChat requires installation from source with additional steps for Rust and CMake on + Mac. ### Is model_search or FastChat more popular on GitHub? FastChat has more GitHub stars (39,490 vs 3,241). Stars measure visibility, not whether either tool fits your constraints. ### Are model_search and FastChat open source? Yes - both are open-source projects on GitHub (model_search: Apache-2.0, FastChat: Apache-2.0). ### Where can I find alternatives to model_search or FastChat? GraphCanon lists graph-backed alternatives at [model_search alternatives](/tools/google-model-search/alternatives) and [FastChat alternatives](/tools/lm-sys-fastchat/alternatives) ([model_search markdown twin](/tools/google-model-search/alternatives.md), [FastChat markdown twin](/tools/lm-sys-fastchat/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/google-model-search-vs-lm-sys-fastchat.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, model_search or FastChat? model_search: Archived. FastChat: Steady. 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 model_search and FastChat? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [model_search trust report](/tools/google-model-search/trust); [FastChat trust report](/tools/lm-sys-fastchat/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=google-model-search`](/api/graphcanon/graph?tool=google-model-search) - 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/_