Train and run open AI models locally with Unsloth Studio, for founders. 68k+ GitHub stars
intermediateโฑ 30 minutes๐ต Free
68,859 stars6,202 forksPythonQuality 8/10Updated 7/25/2026100% free ยท open source
What it is
Builds a web UI for training and running open models like Gemma 4 locally.
What you can make with it
Automations like a chat app that responds based on text inputs using LLMs like Gemma 4.
How it helps
Saves time and effort compared to using the command line for these models, making the process more user-friendly.
Real use case example
"A founder uses Unsloth Studio to build a basic chat app that responds to users' queries, training a model overnight and deploying it in the morning."
If you're new
Beginners can pick up Unsloth Studio as their first exploration into open models and web UIs.
If you're senior
Senior engineers and professionals will appreciate Unsloth Studio for its ease of use and compatibility with various open models.
Common confusion cleared up
Unsloth Studio doesn't deploy models directly to production, you'll need to do that after running them within the UI.
Best inside these AI tools
Claude DesktopSelf-hostedAny AI Client
Pairs with
Stripe webhookNotion databaseClaude API
Why we list it on WorkflowStacks: Unsloth Studio is a free and open-source addition to the marketplace, allowing users to train and deploy open models in a more accessible way.
What it does
Unsloth allows founders to train and run open AI models like Gemma 4, Qwen3.6, DeepSeek, and gpt-oss locally using a web UI
Install / run
git clone https://github.com/unslothai/unsloth.git && cd unsloth
When to use it
โขWhen you want to use open AI models without relying on cloud services
โขWhen you need to train AI models with sensitive data that cannot be shared publicly
โขWhen you want to reduce the latency and costs associated with cloud-based AI model deployment
Quick start
1Run `python app.py` to start the Unsloth Studio web UI
2Open a web browser and navigate to `http://localhost:8000` to access the Unsloth Studio interface
3Select a pre-trained model like Gemma 4 or Qwen3.6 from the model list
4Upload your dataset to fine-tune the selected model
5Configure the training parameters and start the training process
Ready-to-paste prompt
Run `python train.py --model gemma4 --train_data_path /path/to/train/data` to fine-tune the Gemma 4 model with your custom dataset
Heads up: Make sure you have the required Python version (3.8 or higher) and the necessary dependencies installed, including `transformers` and `torch`, before running Unsloth
Saves to your device
Topics
agent
deepseek
fine-tuning
gemma
gemma3
gpt-oss
llama
llama3
llm
llms
mistral
openai
qwen
reinforcement-learning
self-hosted
text-to-speech
tts
ui
unsloth
What's inside โ free to inspect
No purchase needed
Read the entire source before you build โ unlike paid marketplaces that hide it behind a buy button.