unsloth

unslothai/unsloth

GUI app to run and train large language models and diffusion models locally

Why pick itSupports multiple model formats and GPU acceleration

Install

Run LLMs, GGUF and diffusion models such as Qwen, DeepSeek and Gemma locally
Fine-tune LLM, TTS and embedding models with less VRAM, including LoRA, QLoRA, GRPO and DPO
Point Claude Code or Codex at local models with commands like unsloth start claude
Export models to GGUF, FP8 and other formats, or serve them through an OpenAI-compatible API

Run curl -fsSL https://unsloth.ai/install.sh | sh (use the PowerShell command on Windows, or download Unsloth Desktop)
Open Unsloth and pick a model to run or train
To connect an agent, run unsloth start claude or unsloth start codex

Works on Windows, Linux, WSL and macOS with NVIDIA, AMD and Intel GPUs, multi-GPU setups, CPUs or the Vulkan backend.

Summarized by AI from the project docs; check the official docs before relying on it.

rtkRun locally · ★ 84.5k
CLI proxy that reduces LLM token consumption by 60-90%
OllamaRun locally · ★ 185k
Download and run open-weight models like Qwen, DeepSeek, Gemma and gpt-oss locally with one command, with an OpenAI-compatible API.
Open WebUIRun locally · ★ 157k
A self-hosted ChatGPT-style web UI that connects to Ollama and any OpenAI-compatible API, with built-in RAG, web search, multi-user support and MCP.
Cherry StudioRun locally · ★ 52.9k
A cross-platform desktop AI client that puts many cloud models and local Ollama in one interface, with a built-in knowledge base, MCP, agents and 300+ assistant templates.
JanRun locally · ★ 45.1k
A ChatGPT-style desktop app that runs fully offline, with built-in model downloads and the llama.cpp engine; can also switch to cloud APIs.