Unsloth: Easily run and train models locally

Unsloth launched Unsloth Studio, a desktop application for Mac and Windows that runs AI models offline, supporting GGUF and Safetensors formats with tool-calling, web search, and an OpenAI-compatible API. The tool enables side-by-side model comparison, dataset creation from documents, and optimized training for over 500 models, while also offering a free open-source version for fine-tuning on NVIDIA GPUs via Google Colab or Kaggle.

Unsloth Studio runs 100% offline on your Mac and Windows device. Run GGUF and Safetensors models with tool-calling, web search, and OpenAI compatible API. Compare models side by side and upload images, docs, audio, code files and more. Auto-create datasets from PDF, CSV, JSON docs and start training with real-time observability. Unsloth's custom kernels supports optimized training for LoRA, FP8, FFT, PT and 500+ models including text, vision, audio and embeddings. Chat with and compare 2 different models, such as a base model and a fine-tuned one, to see how their outputs differ. Just load your first GGUF/model, then the second, and voilà Data Recipes transforms your docs into useable datasets via graph-node workflow. Upload unstructured or structured files like PDFs, CSV and JSON. Unsloth Data Recipes auto turns documents into your desired formats. Export any model, including your fine-tuned models, to safetensors, or GGUF for use with llama.cpp, vLLM, Ollama, and more. Why not try our fully free open source version? Finetune 2X faster on a single NVIDIA GPU for free on Google Colab or Kaggle Notebooks.