The open-source AI projects that matter right now — stars, licence and what each one does.
5 repositories
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A high-throughput and memory-efficient inference and serving engine for LLMs
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, FLUX and more.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
Star counts are a snapshot, not a live feed — they are refreshed when the directory is updated, so the number here matches the one in our articles and videos.