Unsloth
Easily run & train models locally with no-code interface
Unsloth is an open-source, no-code web UI that lets users train, run, and export open AI models entirely offline on Mac and Windows. It supports LoRA fine-tuning, dataset creation from documents, and model comparison through a unified local interface. Users can also export fine-tuned models to formats compatible with tools like Ollama, vLLM, and llama.cpp.
Unsloth provides a local desktop app with a no-code UI for running GGUF/Safetensors models, auto-generating datasets from documents, and fine-tuning models with optimized custom kernels on consumer hardware.
developers and researchers who want to train and run AI models locally without coding
Background.
- Status
- launched
- Business model
- open-source
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.