Run & Build with AI

• Run and train LLMs, MLX, GGUF, diffusion, embedding, audio models: Qwen3.8, GLM-5.3-Flash, Kimi K3, MiniMax-H3, DeepSeek-V4, Gemma 4.
• Agents & Tools: Use local models with Claude Code, Codex, and MCP, including tool calling and code execution.
• Search & RAG: Use private and unlimited web search, deep research, auto-compaction (rolling context window) and RAG.
• Image and video: Run and train image and video diffusion or multimodal models
• Remote & LAN: Access your local models from any device on LAN or remotely through secure Cloudflare HTTPS.
• Connect: Serve models through an OpenAI compatible API. Also connect your ChatGPT/Codex subscription and cloud providers

Train & Deploy

• Fine-tuning: Train LLMs, diffusion, TTS, and embedding models 2× faster with 70% less VRAM with no accuracy loss
• Complete support: Supports reinforcement learning, LoRA, QLoRA, full fine tuning, pretraining, RL, GRPO, DPO, and FP8.
• Export & Deploy: Export or Deploy models with including GGUF, NVFP4, FP8 and more formats.
• Datasets: Build datasets from PDFs, CSVs, DOCX files, and more with Data Recipes.

📥 Install

Unsloth can be used in three ways: Unsloth Desktop, the desktop app; Unsloth Studio, the web UI; or Unsloth Core, the code based version.

📥 Advanced Installation

The below advanced instructions are for Unsloth Studio. For Unsloth Core advanced installation, view our docs.

#### Developer / Nightly / Experimental installs: macOS, Linux, WSL: The developer install builds from the main branch, which is the latest (nightly) source.

git clone https://github.com/unslothai/unsloth
cd unsloth
./install.sh --local
unsloth studio -p 8888

UNSLOTH_STUDIO_HOME="$PWD/.studio" ./install.sh --local
UNSLOTH_STUDIO_HOME="$PWD/.studio" unsloth studio -p 8888

cd unsloth && git pull
./install.sh --local
unsloth studio -p 8888

#### Developer / Nightly / Experimental installs: Windows PowerShell: The developer install builds from the main branch, which is the latest (nightly) source.

git clone https://github.com/unslothai/unsloth.git
cd unsloth
Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass
.\install.ps1 --local
unsloth studio -p 8888

$env:UNSLOTH_STUDIO_HOME="$PWD\.studio"; .\install.ps1 --local
$env:UNSLOTH_STUDIO_HOME="$PWD\.studio"; unsloth studio -p 8888

cd unsloth; git pull
.\install.ps1 --local
unsloth studio -p 8888

Advanced launch options

Skip PyTorch (GGUF-only mode):

curl -fsSL https://unsloth.ai/install.sh | UNSLOTH_NO_TORCH=1 sh

$env:UNSLOTH_NO_TORCH=1; irm https://unsloth.ai/install.ps1 | iex

Skip the post-install prompt that starts Unsloth (useful for automated installs):

curl -fsSL https://unsloth.ai/install.sh | UNSLOTH_SKIP_AUTOSTART=1 sh

$env:UNSLOTH_SKIP_AUTOSTART=1; irm https://unsloth.ai/install.ps1 | iex

Keep 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:

curl -fsSL https://unsloth.ai/install.sh | UNSLOTH_ISOLATE_UV_CACHE=1 sh

$env:UNSLOTH_ISOLATE_UV_CACHE=1; irm https://unsloth.ai/install.ps1 | iex

./install.sh --local --isolated-uv-cache

.\install.ps1 --local --isolated-uv-cache

Pinning the Python version:

curl -fsSL https://unsloth.ai/install.sh | UNSLOTH_PYTHON=3.12 sh

$env:UNSLOTH_PYTHON='3.12'; irm https://unsloth.ai/install.ps1 | iex

Install to a custom location with UNSLOTH_STUDIO_HOME:

curl -fsSL https://unsloth.ai/install.sh | UNSLOTH_STUDIO_HOME=/abs/path sh

$env:UNSLOTH_STUDIO_HOME='C:\path'; irm https://unsloth.ai/install.ps1 | iex

Point the frontend build at a corporate npm mirror/proxy with UNSLOTH_NPM_REGISTRY:

UNSLOTH_NPM_REGISTRY=https://artifactory.example.com/api/npm/npm/ ./install.sh --local

$env:UNSLOTH_NPM_REGISTRY='https://artifactory.example.com/api/npm/npm/'; .\install.ps1 --local

Cap Unsloth's native CPU thread pools on high-core hosts: UNSLOTH_CPU_THREADS=8 unsloth studio -p 8888.

Vulkan, custom llama.cpp backends:

You can force the backend during installation:

export UNSLOTH_LLAMA_CPP_BACKEND=vulkan   # or cpu, cuda, rocm, auto
curl -fsSL https://unsloth.ai/install.sh | sh

$env:UNSLOTH_LLAMA_CPP_BACKEND="vulkan"   # or cpu, cuda, rocm, auto
irm https://unsloth.ai/install.ps1 | iex

Uninstall

MacOS, WSL, Linux: curl -fsSL https://raw.githubusercontent.com/unslothai/unsloth/main/scripts/uninstall.sh | sh

Windows (PowerShell): irm https://raw.githubusercontent.com/unslothai/unsloth/main/scripts/uninstall.ps1 | iex

For more info, see our docs.

Deleting model files

You can delete old model files either from the bin icon in model search or by removing the relevant cached model folder from the default Hugging Face cache directory. By default, HF uses:

MacOS, Linux, WSL: ~/.cache/huggingface/hub/

Windows: %USERPROFILE%\.cache\huggingface\hub\