{"data":{"slug":"unslothai-unsloth","name":"unsloth","tagline":"Local UI for running and training LLMs and diffusion models","github_url":"https://github.com/unslothai/unsloth","owner":"unslothai","repo":"unsloth","owner_avatar_url":"https://avatars.githubusercontent.com/u/150920049?v=4","primary_language":"Python","stars":76344,"forks":6962,"topics":["agent","ai","chatgpt","deepseek","fine-tuning","gemma","image-generation","llama","llm","llms","openai","python","qwen","reinforcement-learning","self-hosted","stable-diffusion","text-to-speech","tts","ui","unsloth"],"archived":false,"github_pushed_at":"2026-09-18T08:00:38+00:00","maintenance_label":"Very active","stars_delta_30d":6723,"url":"https://www.graphcanon.com/tools/unslothai-unsloth","markdown_url":"https://www.graphcanon.com/tools/unslothai-unsloth.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/unslothai-unsloth","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=unslothai-unsloth","description":"Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.","homepage_url":"https://unsloth.ai/docs","license":"Apache-2.0","open_issues":1242,"watchers":384,"ai_summary":"Unsloth provides a local UI for running and training various LLMs and diffusion models, including GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, and FLUX. It supports three usage modes: Unsloth Desktop, Unsloth Studio, and Unsloth Core.","readme_excerpt":"## 📥 Install\nUnsloth can be used in three ways: **[Unsloth Desktop](https://unsloth.ai/download)**, the desktop app; **[Unsloth Studio](https://unsloth.ai/docs/new/studio/)**, the web UI; or **Unsloth Core**, the code based version.\n\n---\n\n## 📥 Advanced Installation\nThe below advanced instructions are for Unsloth Studio. For Unsloth Core advanced installation, [view our docs](https://unsloth.ai/docs/get-started/install/pip-install#advanced-pip-installation).\n\n#### Developer / Nightly / Experimental installs: macOS, Linux, WSL:\nThe developer install builds from the `main` branch, which is the latest (nightly) source.\n```bash\ngit clone https://github.com/unslothai/unsloth\ncd unsloth\n./install.sh --local\nunsloth studio -p 8888\n```\nTo install into an isolated location, set `UNSLOTH_STUDIO_HOME`:\n```bash\nUNSLOTH_STUDIO_HOME=\"$PWD/.studio\" ./install.sh --local\nUNSLOTH_STUDIO_HOME=\"$PWD/.studio\" unsloth studio -p 8888\n```\nThen to update:\n```bash\ncd unsloth && git pull\n./install.sh --local\nunsloth studio -p 8888\n```\n\n#### Developer / Nightly / Experimental installs: Windows PowerShell:\nThe developer install builds from the `main` branch, which is the latest (nightly) source.\n```powershell\ngit clone https://github.com/unslothai/unsloth.git\ncd unsloth\nSet-ExecutionPolicy -Scope Process -ExecutionPolicy RemoteSigned\n.\\install.ps1 --local\nunsloth studio -p 8888\n```\nTo install into an isolated location, set `UNSLOTH_STUDIO_HOME`:\n```powershell\n$env:UNSLOTH_STUDIO_HOME=\"$PWD\\.studio\"; .\\install.ps1 --local\n$env:UNSLOTH_STUDIO_HOME=\"$PWD\\.studio\"; unsloth studio -p 8888\n```\nThen to update:\n```powershell\ncd unsloth; git pull\n.\\install.ps1 --local\nunsloth studio -p 8888\n```\n\n#### Advanced launch options\n\nSkip PyTorch (GGUF-only mode):\n```bash\ncurl -fsSL https://unsloth.ai/install.sh | UNSLOTH_NO_TORCH=1 sh\n```\n```powershell\n$env:UNSLOTH_NO_TORCH=1; irm https://unsloth.ai/install.ps1 | iex\n```\n\nSkip the post-install prompt that starts Unsloth (useful for automated installs):\n```bash\ncurl -fsSL https://unsloth.ai/install.sh | UNSLOTH_SKIP_AUTOSTART=1 sh\n```\n```powershell\n$env:UNSLOTH_SKIP_AUTOSTART=1; irm https://unsloth.ai/install.ps1 | iex\n```\n\nKeep the install-time package cache under the Studio directory instead of reusing an existing uv cache. Downloads are slower the first time, and an explicit `UV_CACHE_DIR` still wins over this:\n```bash\ncurl -fsSL https://unsloth.ai/install.sh | UNSLOTH_ISOLATE_UV_CACHE=1 sh\n```\n```powershell\n$env:UNSLOTH_ISOLATE_UV_CACHE=1; irm https://unsloth.ai/install.ps1 | iex\n```\nFor a local run the flag is `--isolated-uv-cache`:\n```bash\n./install.sh --local --isolated-uv-cache\n```\n```powershell\n.\\install.ps1 --local --isolated-uv-cache\n```\n\nPinning the Python version:\n```bash\ncurl -fsSL https://unsloth.ai/install.sh | UNSLOTH_PYTHON=3.12 sh\n```\n```powershell\n$env:UNSLOTH_PYTHON='3.12'; irm https://unsloth.ai/install.ps1 | iex\n```\n\nInstall to a custom location with `UNSLOTH_STUDIO_HOME`:\n```bash\ncurl -fsSL https://unsloth.ai/install.sh | UNSLOTH_STUDIO_HOME=/abs/path sh\n```\n```powershell\n$env:UNSLOTH_STUDIO_HOME='C:\\path'; irm https://unsloth.ai/install.ps1 | iex\n```\n\nPoint the frontend build at a corporate npm mirror/proxy with `UNSLOTH_NPM_REGISTRY`:\n```bash\nUNSLOTH_NPM_REGISTRY=https://artifactory.example.com/api/npm/npm/ ./install.sh --local\n```\n```powershell\n$env:UNSLOTH_NPM_REGISTRY='https://artifactory.example.com/api/npm/npm/'; .\\install.ps1 --local\n```\n\nCap Unsloth's native CPU thread pools on high-core hosts: `UNSLOTH_CPU_THREADS=8 unsloth studio -p 8888`.\n\n#### Vulkan, custom llama.cpp backends:\n\nYou can force the backend during installation: \n```bash\nexport UNSLOTH_LLAMA_CPP_BACKEND=vulkan   # or cpu, cuda, rocm, auto\ncurl -fsSL https://unsloth.ai/install.sh | sh\n```\n```powershell\n$env:UNSLOTH_LLAMA_CPP_BACKEND=\"vulkan\"   # or cpu, cuda, rocm, auto\nirm https://unsloth.ai/install.ps1 | iex\n```\n\n#### Uninstall\n\n**MacOS, WSL, Linux:** `curl -fsSL https://raw.githubusercontent.com/unslothai/unsloth/main/sc","github_created_at":"2023-11-29T16:50:09+00:00","created_at":"2026-07-07T17:30:52.252116+00:00","updated_at":"2026-09-20T04:28:43.776706+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"ai","name":"ai"},{"slug":"chatgpt","name":"chatgpt"},{"slug":"deepseek","name":"deepseek"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"gemma","name":"gemma"},{"slug":"image-generation","name":"image-generation"},{"slug":"llm","name":"llm"}],"trust":{"provenance":{"is_fork":false,"github_id":725205304,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:09:38.679Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":23,"days_since_push":0,"last_release_at":"2026-09-17T14:37:04Z","stars_delta_30d":6723,"open_issues_delta_30d":195},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-20T04:00:34.628Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:09:37.558Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-18T08:09:37.558Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-18T08:09:37.558Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-18T08:09:37.558Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need a local UI for running and training specific models like GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, and FLUX.","If you prefer a tool that supports multiple usage modes, including a desktop app, web UI, and a code-based version.","When you require advanced installation options, such as isolating the installation location or pinning the Python version.","For developers who want to use the latest nightly builds from the main branch for cutting-edge features and updates."],"when_not_to_use":["If you are working with models not supported by Unsloth, such as those not listed in its summary.","When you need a tool that does not require local installation and can be used entirely in the cloud.","If you are looking for a tool that does not offer a desktop app or web UI interface and prefer a purely command-line interface.","When you do not need the flexibility of advanced installation options and prefer a simpler setup process."],"source":"enrich:decision_facts","observed_at":"2026-09-18T12:15:40.116Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Unsloth is a local UI tool for running and training various LLMs and diffusion models, including GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, and FLUX. It supports three usage modes: Unsloth Desktop, Unsloth, a,"}]}}