CAJAL is a local scientific paper generator that runs entirely on consumer hardware. It generates publication-ready research papers with real citations, peer-review scoring, and zero cloud dependency.
Key Highlights
🏆Ranked #3 on P2PCLAW scientific paper benchmark (beaten only by Claude Sonnet 4.6)
🧠Local 9B model (CAJAL-9B v2) with multiple quantizations (Q4_K_M, Q6_K, Q8_0, F16)
Thanks for sharing CAJAL. We generally do not accept issues or listing requests for standalone models or external projects. This repo is focused on self-contained, runnable LLM app tutorials with code in their own folder.
If you'd like this considered, please submit a PR with a complete tutorial app that uses CAJAL in a practical workflow, includes setup and run instructions, and is not just a project listing. Otherwise this is not something we can add as-is.
<!-- gh-comment-id:4467943935 -->
@awesomekoder commented on GitHub (May 16, 2026):
Thanks for sharing CAJAL. We generally do not accept issues or listing requests for standalone models or external projects. This repo is focused on self-contained, runnable LLM app tutorials with code in their own folder.
If you'd like this considered, please submit a PR with a complete tutorial app that uses CAJAL in a practical workflow, includes setup and run instructions, and is not just a project listing. Otherwise this is not something we can add as-is.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @Agnuxo1 on GitHub (May 6, 2026).
Original GitHub issue: https://github.com/Shubhamsaboo/awesome-llm-apps/issues/784
📝 Proposal: Add CAJAL — Local Scientific Paper Generation Model (4B-9B, Ranked #3)
Project: CAJAL — Cognitive Academic Journal Authoring Layer
Why CAJAL Fits This List
CAJAL is a local scientific paper generator that runs entirely on consumer hardware. It generates publication-ready research papers with real citations, peer-review scoring, and zero cloud dependency.
Key Highlights
Model Zoo (HuggingFace)
Quick Start
Author
Would love to contribute to this list! Happy to open a PR if preferred.
@awesomekoder commented on GitHub (May 16, 2026):
Thanks for sharing CAJAL. We generally do not accept issues or listing requests for standalone models or external projects. This repo is focused on self-contained, runnable LLM app tutorials with code in their own folder.
If you'd like this considered, please submit a PR with a complete tutorial app that uses CAJAL in a practical workflow, includes setup and run instructions, and is not just a project listing. Otherwise this is not something we can add as-is.