Unsloth Documentation llms.txt · AI Docs Browser · mdream [llms.txt Tools](https://mdream.dev/llms-txt/unsloth/llms-txt) # Unsloth Documentation llms.txt Browse Unsloth Documentation documentation as markdown. Click any page in the sidebar to view it, or copy the full llms.txt for your AI tools. unsloth.ai/llms.txt [Raw llms.txt](https://unsloth.ai/docs/llms.txt) [Raw llms-full.txt](https://unsloth.ai/llms-full.txt) Copy Markdown [](https://unsloth.ai/llms.txt) llms.txt 🇺🇸 English Unsloth Docs Unsloth Model Catalog Fine-tuning for Beginners Unsloth Requirements FAQ + Is Fine-tuning Right For Me? Unsloth Notebooks Unsloth Installation Install Unsloth via pip and uv Install Unsloth on MacOS How to Fine-Tune LLMs on Windows with Unsloth (Step-by-Step Guide) Install Unsloth via Docker Updating Unsloth Fine-tuning LLMs on AMD GPUs with Unsloth Guide AMD AI Reinforcement Learning Hackathon with Unsloth Fine-tuning LLMs on Intel GPUs with Unsloth Conda Install How to Fine-tune LLMs in VS Code with Unsloth & Colab GPUs Google Colab Fine-tuning LLMs Guide Datasets Guide LoRA fine-tuning Hyperparameters Guide What Model Should I Use for Fine-tuning? Tutorial: How to Finetune Llama-3 and Use In Ollama Reinforcement Learning (RL) Guide Reinforcement Learning GRPO with 7x Longer Context Vision Reinforcement Learning (VLM RL) FP8 Reinforcement Learning Tutorial: Train your own Reasoning model with GRPO Advanced Reinforcement Learning Documentation GSPO Reinforcement Learning RL Reward Hacking https://arxiv.org/pdf/2510.26788 Memory Efficient RL Preference Optimization Training - DPO, ORPO & KTO Training AI Agents with RL Introducing Unsloth Studio Get started with Unsloth Studio How to Run models with Unsloth Studio Unsloth Studio Installation Unsloth Data Recipes Export models with Unsloth Studio Unsloth Updates Large language model (LLMs) Tutorials Qwen3 - How to Run & Fine-tune Qwen3-VL: How to Run Guide Qwen3-2507: Run Locally Guide MiniMax-M2.7 - How to Run Locally GLM-5: How to Run Locally Guide Kimi K2.5: How to Run Locally Guide GLM-4.7-Flash: How To Run Locally Gemma 3 - How to Run Guide Gemma 3n: How to Run & Fine-tune Qwen3-Coder: How to Run Locally MiniMax-M2.5: How to Run Guide DeepSeek-OCR 2: How to Run & Fine-tune Guide GLM-4.7: How to Run Locally Guide How to Run Qwen-Image-2512 Locally in ComfyUI Run Qwen-Image-2512 in stable-diffusion.cpp Tutorial Devstral 2 - How to Run Guide Ministral 3 - How to Run Guide DeepSeek-OCR: How to Run & Fine-tune Kimi K2 Thinking: Run Locally Guide GLM-4.6: Run Locally Guide Qwen3-Next: Run Locally Guide FunctionGemma: How to Run & Fine-tune DeepSeek-V3.1: How to Run Locally DeepSeek-R1-0528: How to Run Locally Liquid LFM2.5: How To Run & Fine-tune Magistral: How to Run & Fine-tune IBM Granite 4.0 Llama 4: How to Run & Fine-tune Grok 2 Devstral: How to Run & Fine-tune How to Run Local LLMs with Docker: Step-by-Step Guide DeepSeek-V3-0324: How to Run Locally DeepSeek-R1: How to Run Locally DeepSeek-R1 Dynamic 1.58-bit Phi-4 Reasoning: How to Run & Fine-tune QwQ-32B: How to Run effectively Cogito v2.1: How to Run Locally GLM-5.2 - How to Run Locally Qwen3.6 - How to Run Locally Gemma 4 - How to Run Locally Gemma 4 QAT Gemma 4 Fine-tuning Guide DeepSeek-V4: How to Run Locally Inkling - How to Run Locally Kimi K2.7 Code - How to Run Locally How to Run MTP Models: Multi-Token Prediction Guide DiffusionGemma - How to Run Locally MiniMax M3 - How to Run Locally Qwen3.5 - How to Run Locally Qwen3.5 Fine-tuning Guide Qwen3.5 GGUF Benchmarks Kimi K2.6 - How to Run Locally NVIDIA Nemotron 3 Ultra - How To Run Locally NVIDIA Nemotron 3 Nano Omni - How To Run Locally Mistral 3.5 - How To Run Locally IBM Granite 4.1 - How to Run Locally GLM-5.1 - How to Run Locally Qwen3-Coder-Next: How to Run Locally NVIDIA Nemotron 3 Nano - How To Run Guide NVIDIA Nemotron-3-Super: How To Run Guide gpt-oss: How to Run Guide gpt-oss Reinforcement Learning Tutorial: How to Train gpt-oss with RL Tutorial: How to Fine-tune gpt-oss Long Context gpt-oss Training How to use Unsloth as an API endpoint Inference & Deployment Saving to GGUF Speculative Decoding vLLM Deployment & Inference Guide vLLM Engine Arguments LoRA Hot Swapping Guide Saving models to Ollama Deploying models to LM Studio How to install LM Studio CLI in Linux Terminal SGLang Deployment & Inference Guide Unsloth Inference llama-server & OpenAI endpoint Deployment Guide How to Run and Deploy LLMs on your iOS or Android Phone Troubleshooting Inference Deploying LLMs with Hugging Face Jobs How to Run Local LLMs with Claude Code How to Run Local LLMs with OpenAI Codex Run Unsloth Dynamic NVFP4 Guide How to Use MCP Servers with Local LLMs Multi-GPU Fine-tuning with Unsloth Multi-GPU Fine-tuning with Distributed Data Parallel (DDP) Fine-tuning Embedding Models with Unsloth Guide Fine-tune MoE Models 12x Faster with Unsloth Text-to-Speech (TTS) Fine-tuning Guide Unsloth Dynamic 2.0 GGUFs Unsloth Dynamic GGUFs on Aider Polyglot Tool Calling Guide for Local LLMs Vision Fine-tuning Troubleshooting & FAQs Hugging Face Hub, XET debugging Chat Templates Unsloth Environment Flags Continued Pretraining Finetuning from Last Checkpoint Unsloth Benchmarks Run Coding Agents with Local LLMs using Unsloth Start Connect API Providers & Model Servers to Unsloth Connect OpenAI to Unsloth: Run GPT Models in Local Chat Connect Anthropic to Unsloth: Run Claude Models in Local Chat Connect llama.cpp to Unsloth: Run GGUFs with llama-server Connect vLLM to Unsloth for Local Chat Inference How to Connect Ollama to Unsloth How to Connect OpenRouter to Unsloth: API Key & Model Setup How to Run Local AI Models with Hermes Agent How to Run Local AI Models with OpenClaw How to Run Local AI Models with OpenCode Connect Python SDK to Unsloth Connect Curl & HTTP to Unsloth 3x Faster LLM Training with Unsloth Kernels + Packing 500K Context Length Fine-tuning Quantization-Aware Training (QAT) Fine-Tuning LLMs on NVIDIA DGX Station with Unsloth How to Fine-tune LLMs with Unsloth & Docker Fine-tuning LLMs with NVIDIA DGX Spark and Unsloth Fine-tuning LLMs with Blackwell, RTX 50 series & Unsloth How to Run Diffusion Image GGUFs in ComfyUI AI Engineer's 2025 Unsloth - AI Engineer World's Fair 2026 GPU Mode - Reinforcement Learning Mini Conference 2026 Unsloth AMD PyTorch Synthetic Data Hackathon PyTorch Conference 2025 - Unsloth Querying This Documentation ## What is Unsloth Documentation's llms.txt? Unsloth Documentation publishes an `/llms.txt` file that provides AI systems with a structured index of its documentation. It follows the [llms.txt specification](https://llmstxt.org), organizing links to guides, API references, and tutorials under section headings so that LLMs like ChatGPT, Claude, and Gemini can quickly understand what Unsloth Documentation offers and where to find details. Issues Spec 2 Sections 170 Links 30.0 KB Size ~7.7k Tokens Sections: 🇺🇸 English · Querying This Documentation ## Add Unsloth Documentation Docs to Your AI Assistant Select your tool to see how to add Unsloth Documentation's llms.txt as a documentation source. Cursor Windsurf Claude Code ChatGPT Zed Copilot 1. 1 Open any chat or composer panel 2. 2 Type @Docs and select "Add new doc" 3. 3 Paste the URL: https://unsloth.ai/llms.txt 4. 4 Wait for the green dot (indexing complete) 5. 5 Reference @Docs in chat when asking about Unsloth Documentation Cursor crawls the URL and indexes all subpages. Add a trailing slash to index child pages too. ## Spec Compliance 1 error ## Frequently Asked Questions Where is Unsloth Documentation's llms.txt file? Unsloth Documentation publishes its llms.txt at https://unsloth.ai/llms.txt. This file provides a structured, markdown-formatted index of Unsloth Documentation's documentation that AI systems can consume to understand the project's APIs, guides, and references. How do I use Unsloth Documentation's llms.txt with AI coding assistants? Copy the llms.txt content and paste it into your AI assistant (Cursor, Windsurf, Claude, ChatGPT) as context. This gives the AI an accurate map of Unsloth Documentation's documentation so it can provide better code suggestions and answers about Unsloth Documentation. What does Unsloth Documentation's llms.txt contain? Unsloth Documentation's llms.txt contains 2 sections and 170 documentation links in 30.0 KB (~7.7k tokens). Key sections include 🇺🇸 English, Querying This Documentation. How many tokens does Unsloth Documentation's llms.txt use? The concise llms.txt index is approximately 7.7k tokens (30.0 KB). Most AI assistants can fit this within their context window. For the full expanded documentation, look for an llms-full.txt variant which embeds all content inline. What is Unsloth Documentation? Unsloth Studio is a web UI for training and running open models like Qwen, DeepSeek, gpt-oss and Gemma locally.. Unsloth Documentation's llms.txt file helps AI systems understand this by providing a structured overview of its documentation, making it easier for developers to get accurate AI-assisted help when working with Unsloth Documentation. Can I generate an llms.txt for my own project? Yes. Use the free llms.txt generator at mdream.dev/tools/llms-txt/generator to crawl your site and produce a spec-compliant llms.txt file. You can also validate existing files with the llms.txt validator. ## Browse More llms.txt Files [WorkOS Documentation WorkOS provides developer-friendly APIs for enterprise features like Single Sign-On, Directory Sync, User Management, Admin Portal, Audit Logs, and more. This documentation site helps developers implement these features.](https://mdream.dev/llms-txt/unsloth/llms-txt/workos) [ElevenLabs Documentation](https://mdream.dev/llms-txt/unsloth/llms-txt/elevenlabs) [Checkly Docs Puppeteer example scripts for running Headless Chrome from Node.](https://mdream.dev/llms-txt/unsloth/llms-txt/puppeteer-examples) [DigitalOcean Documentation Comprehensive tutorials, references, example code, and more for DigitalOcean products.](https://mdream.dev/llms-txt/unsloth/llms-txt/digitalocean) [MCP Toolbox for Databases - Documentation Index MCP Toolbox for Databases is an open source MCP server for databases. It enables you to develop tools easier, faster, and more securely by handling the complexities such as connection pooling, authentication, and more.](https://mdream.dev/llms-txt/unsloth/llms-txt/genai-toolbox) [Awesome Python The **#10 most-starred repo on GitHub**. Put your product in front of Python developers. \[Become a sponsor\](SPONSORSHIP.md).](https://mdream.dev/llms-txt/unsloth/llms-txt/awesome-python) [Opik Documentation Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.](https://mdream.dev/llms-txt/unsloth/llms-txt/opik) [Weights & Biases Documentation](https://mdream.dev/llms-txt/unsloth/llms-txt/wandb) [View all 99 projects ](https://mdream.dev/llms-txt/unsloth/llms-txt) ## Related Tools [

llms.txt Generator

Generate an llms.txt for your own project.](https://mdream.dev/llms-txt/unsloth/tools/llms-txt/generator) [

llms.txt Validator

Validate your llms.txt against the official spec.](https://mdream.dev/llms-txt/unsloth/tools/llms-txt/validator) © 2026 [Harlan Wilton](https://github.com/harlan-zw) · [MIT](https://github.com/harlan-zw/mdream/blob/main/license) [GitHub](https://github.com/harlan-zw/mdream) [Discord](https://discord.com/invite/275MBUBvgP)