Unsloth
unsloth.aiEasily run & train models locally with no-code interface
AI Toolsllmfine-tuninglocal-aiopen-sourceno-codemodel-traininggguf
About
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.
Problem
Training and running open-source AI models locally requires complex setup and coding expertise that most users lack.
For
developers and researchers who want to train and run AI models locally without coding
How it works
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.
Business model
open-source
Status
launched