🦥Introducing Unsloth Studio
Run and train AI models locally with Unsloth Studio.
We’re launching Unsloth Studio (Beta): an open-source, no-code web UI for training, running and exporting open models in one unified local interface.
Run GGUF and safetensor models locally on Mac, Windows, Linux.
Train 500+ models 2x faster with 70% less VRAM (no accuracy loss)
Run and train text, vision, TTS audio, embedding models
MacOS: Training, MLX and GGUF inference all work inside of Unsloth.
No dataset needed. Auto-create datasets from PDF, CSV, JSON, DOCX, TXT files.
Connect your local models to any agent including Claude Code, Codex, Hermes and more.
Export or save your model to GGUF, 16-bit safetensor etc.
Self-healing tool calling / advanced web search + code execution
Auto inference settings, edit chat templates, use Unsloth as an API endpoint.
For all the latest updates, see our new changelog page here! ✨
⭐ Features
Execute code + heal Tool calling
Unsloth Studio lets LLMs run Bash and Python, not just JavaScript with bypass permissions. It also sandboxes programs like Claude Artifacts so models can test code, generate files, and verify answers with real computation.
E.g. Unsloth creates a sandbox to allow GLM-5.2 to execute code which shows as HTML preview in Canvas.
Web search upgraded
Unsloth's private, unlimited and secure web search actually visits pages directly to collect relevant information and data and doesn't just scan through website summaries. This provides outputs much more accurate / in-depth info and context.
E.g. Qwen3.5-4B searched 20+ websites and cited sources, with web search happening inside its thinking trace.
Unsloth as an API endpoint
You can now use local LLMs via tools like Claude Code and Codex by connecting it to Unsloth's API endpoint. This means you'll be able to directly run Qwen and Gemma models in those tools with Unsloth's inference which includes features like self-healing tool-calling, websearch etc.
You can also connect a provider like OpenAI, Anthropic or vLLM to Unsloth.
No-code training
Upload PDF, CSV, JSON docs, or YAML configs and start training instantly on NVIDIA. Unsloth’s kernels optimize LoRA, FP8, FFT, PT across 500+ text, vision, TTS/audio and embedding models.
Fine-tune the latest LLMs like Qwen3.5 and NVIDIA Nemotron 3. Multi-GPU works automatically, with a new version coming.
Run models locally
Search and run GGUF and safetensor models with self-healing tool calling, advanced web search, auto inference settings, code execution (Bash + Python), APIs. Upload images, docs, audio, code.
Battle models side by side. Powered by llama.cpp + Hugging Face, Unsloth supports multi-GPU inference, automatic offloading and fitting and most models.
Data Recipes
Data Recipes transforms your docs into useable / synthetic datasets via graph-node workflow. Upload unstructured or structured files like PDFs, CSV and JSON. Unsloth Data Recipes, powered by NVIDIA Nemo Data Designer, auto turns documents into your desired formats.
Observability
Gain complete visibility into and control over your training runs. Track training loss, gradient norms, and GPU utilization in real time, and customize to your liking.
You can even view the training progress on other devices like your phone.
Export / Save models
Export any model, including your fine-tuned models, to safetensors, or GGUF for use with llama.cpp, vLLM, Ollama, LM Studio, and more.
Stores your training history, so you can revisit runs, export again and experiment.
Model Arena
Chat with and compare 2 different models, such as a base model and a fine-tuned one, to see how their outputs differ.
Just load your first GGUF/model, then the second, and voilà! Inference will firstly load for one model, then the second one.
Privacy first + Secure
Unsloth Studio can be used 100% offline and locally on your computer. Its token-based authentication, including encrypted password and JWT access / refresh flows keeps your data secure.
You can use pre-exisiting / old models or GGUFs that previously downloaded from HF etc. Read instructions here.
Please note this is the BETA version of Unsloth Studio. Expect many improvements, fixes, and new features in the coming days and weeks.
⚡ Quickstart
Unsloth Studio works on Windows, Linux, WSL and MacOSx.
CPU: Unsloth still works without a GPU, but only for Chat inference and Data Recipes.
Training: Works on NVIDIA, Intel, Apple, and AMD GPUs
Mac: Training, MLX and GGUF inference are ALL supported.
Inference: supported for nearly all devices and hardware
Multi-GPU: Works already, with a major upgrade on the way.
Install with Unsloth Desktop
The easiest way to install Unsloth Studio is with the native Desktop app. Download it for your operating system:
For a manual Unsloth Studio installation, use the commands below. Run the same command again to update:
MacOS, Linux, WSL:
Windows PowerShell:
Launch Unsloth
Launch Unsloth securely with HTTPS and Cloudflare
NEW! Unsloth now provides a secure way to launch Unsloth over HTTPS through a free Cloudflare tunnel. Use the below (works in Windows, Mac & Linux):
For more details about install and uninstallation please visit the Unsloth Studio Install section.
InstallationGoogle Colab notebook
We’ve created a free Google Colab notebook so you can explore all of Unsloth’s features on Colab’s T4 GPUs. You can train and run most models up to 22B parameters, and switch to a larger GPU for bigger models. Just Click 'Run all' and the UI should pop up after installation.
Once installation is complete, scroll to Start Unsloth Studio and click Open Unsloth Studio in the white box shown on the left:
Scroll further down, to see the actual UI.
Sometimes the Unsloth link may return an error. This happens because you might have disabled cookies or you're using an adblocker or Mozilla. You can still access the UI by scrolling below the button.
👾 Unsloth Start
Unsloth Start lets you connect Claude Code, Codex and other agents to local models via the unsloth start command.
Start Unsloth, load a model, open your project folder, and then run:
Replace claude with any agent below:
Claude Code
unsloth start claude
OpenAI Codex
unsloth start codex
Hermes Agent
unsloth start hermes
OpenClaw
unsloth start openclaw
OpenCode
unsloth start opencode
Workflow
Here is a usual workflow of Unsloth Studio to get you started:
Launch Unsloth from install instructions.
Load a model from local files or a supported integration.
Import training data from PDFs, CSVs, or JSONL files, or build a dataset from scratch.
Clean, refine, and expand your dataset in Data Recipes.
Start training with recommended presets or customize the config yourself.
Chat with the trained model and compare its outputs against the base model.
Save or export locally to the stack you already use.
You can read our individual deep dives into each section of Unsloth Studio:
FAQ
Does Unsloth collect or store data? Unsloth does not collect usage telemetry. Unsloth only collects the minimal hardware information required for compatibility, such as GPU type and device (e.g. Mac). Unsloth Studio runs 100% offline and locally.
How do I use an old / exisiting model that I downloaded previously from Hugging Face? Yes, you can use pre-exisiting/old models or GGUFs that you previously downloaded from Hugging Face etc. They should be now be automatically detected by Unsloth otherwise read our instructions here.
Why is inference sometimes slower in Unsloth? Unsloth, like other local inference apps, are powered by llama.cpp, so speeds should be mostly the same. Sometimes Unsloth might be because you turned on web-search, code execution, self-healing tool-calling on. All these features may make your inference slower. If the speed difference is still slower with all features turned off, please make a GitHub issue!
Does Unsloth Studio support OpenAI-compatible APIs? Yes, see our API endpoint guide here.
Is Unsloth now licensed under AGPL-3.0? Unsloth uses a dual-licensing model of Apache 2.0 and AGPL-3.0. The core Unsloth package remains licensed under Apache 2.0, while certain optional components, such as the Unsloth Studio UI are licensed AGPL-3.0.
This structure helps support ongoing Unsloth development while keeping the project open source and enabling the broader ecosystem to continue growing.
Does Unsloth only support LLMs?
No. Unsloth supports a range of supported transformers compatible model families, including text, multimodal models, text-to-speech, audio, embeddings, and BERT-style models.
Can I use my own training config? Yes. Import a YAML config and Unsloth will pre-fill the relevant settings.
Do you need to train models to use the UI? No, you can just download any GGUF or model without fine-tuning any model.
Future of Unsloth
We're working hard to make open-source AI as accessible as possible. Coming next for Unsloth and Unsloth Studio, we're releasing official support for: multi-GPU, Apple Silicon/MLX and AMD. Reminder this is the BETA version of Unsloth Studio so expect a lot of announcements and improvements in the coming weeks. We’re also working closely with NVIDIA on multi-GPU support to deliver the best and simplest experience possible.
Acknowledgements
A huge thank you to NVIDIA and Hugging Face for being part of our launch. Also thanks to all of our early beta testers for Unsloth Studio, we truly appreciate your time and feedback. We’d also like to thank llama.cpp, PyTorch and open model labs for providing the infrastructure that made Unsloth Studio possible.
Last updated
Was this helpful?
