Awesome-Chinese-LLM

Why we included this project

Anyone working with Chinese-language models will find this index a fast way to see what the ecosystem actually contains. It collects open-source base models, domain-specific fine-tunes, datasets, and tutorials, with a deliberate bias toward smaller models that can be deployed privately and fine-tuned without a huge budget, rather than only the largest frontier systems. The comparison tables are the real draw: they line up parameter sizes, training token counts, context lengths, and commercial-use status across families like ChatGLM, Qwen, Baichuan, and DeepSeek. Since it is a community-maintained list rather than a single tool, its value is in curation. You can quickly tell which base models are safe to use commercially, which vertical fine-tunes exist, and where to find training data and tutorials. That makes it a sensible first stop before digging into individual model repositories.