Vibe Coding Discoverunsloth
View on GitHubLocal UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
Unsloth is a Python training and inference stack plus desktop/web UI for running, fine-tuning and RL-training LLMs and diffusion models 2x faster with less VRAM. Supports LoRA/QLoRA/full fine-tuning, GGUF/MLX export, local OpenAI-compatible serving, RAG and agent hooks. Apache-2.0.
Use Cases
Fine-tune LLMs on a single consumer GPURun local GGUF/MLX models from a desktop UIReinforcement learning and GRPO/DPO trainingExport trained models to GGUF/FP8/NVFP4Serve local models via OpenAI-compatible APIConnect Claude Code or Codex to local modelsPrivate RAG and web search over local modelsTrain image and video diffusion modelsTrain TTS and embedding modelsBuild datasets from PDFs/CSVs/DOCX
Built With
- Language
- Python
- Frameworks
- PyTorch · Hugging Face Transformers · TRL · PEFT · bitsandbytes · llama.cpp · MLX · vLLM · Tauri · Docker · Typer
Tags
fine-tuning · llm · lora · qlora · grpo · reinforcement-learning · gguf · quantization · inference · local-llm · diffusion · tts · training · desktop-app · openai-api · mcp