Unsloth AI

Unsloth AI develops Unsloth, an open-source framework for fine-tuning and reinforcement learning of large language models. Its stated mission is to make AI as accurate and accessible as possible. The framework streamlines local training, evaluation, saving, and deployment with Ollama, llama.cpp, and vLLM, and supports training and deploying models such as DeepSeek, gpt-oss, Llama, Qwen, and Gemma. It serves developers and practitioners who want to train their own models locally, with free notebooks available for guided use.