What do you want to do?
3 use cases
-
Chat with an AI model fully offline
Install Jan, download an open model from Hugging Face and chat without sending anything to the cloud.
- REPO
janhq/jan - Personal productivity
- Beginner
View prompt
Help me set up janhq/jan on my <OS> computer with <RAM> of memory. Recommend a local model size that will run smoothly and walk me through downloading it and starting a chat.
- REPO
-
Use Jan as a local OpenAI-compatible API
Turn on Jan's local server and point your scripts or apps at localhost:1337.
View prompt
Using janhq/jan's OpenAI-compatible server at localhost:1337, change my <script or app> to call the local model <model> instead of the OpenAI API, run it, and compare the answer to the cloud version.
-
Build Jan from source with your GPU engine
Clone Jan and build it with make, choosing a CUDA, Vulkan, Metal or ROCm engine variant.
View prompt
Build janhq/jan from source on this machine with the <engine variant> engine using make dev. If the build fails, read the error and apply the fix the README gives for that case.
Quick start with Jan
- Check you have what it needs: Windows 10+, macOS 13.6+ or most Linux distributions; RAM for the model size: 8GB for 3B models, 16GB for 7B, 32GB for 13B on macOS; To build from source: Node.js 20+, Yarn 4.5.3+, Make and Rust.
- Open janhq/jan on GitHub and read the README and license.
- Download Jan for your OS from Jan.ai or GitHub Releases: Jan.exe, Jan.dmg, Jan.deb or Jan.AppImage
- Open Jan and download a model such as Llama, Gemma or Qwen from Hugging Face
- Pick a model size your RAM can handle, for example 3B on an 8GB Mac
- Start chatting; everything runs locally when you choose a local model
These steps come from our top use case, Chat with an AI model fully offline, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for janhq/jan
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forPeople who want a private ChatGPT-style app on their own computer, and developers who want a local OpenAI-compatible endpoint.
- Why it is hot45k stars, talked about in 2 AI sources we track
- LanguageRust
- Sourcegithub.com/janhq/jan ยท Back to Hot repos
Requirements
- Windows 10+, macOS 13.6+ or most Linux distributions
- RAM for the model size: 8GB for 3B models, 16GB for 7B, 32GB for 13B on macOS
- To build from source: Node.js 20+, Yarn 4.5.3+, Make and Rust
Add this badge to your README
Maintain Jan? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/janhq-jan/?utm_source=github&utm_medium=badge&utm_campaign=janhq-jan)
HTML
<a href="https://dedupedai.com/use-cases/janhq-jan/?utm_source=github&utm_medium=badge&utm_campaign=janhq-jan"><img src="https://dedupedai.com/badge/janhq/jan.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Jan
What is Jan?
Jan is an open-source ChatGPT replacement that downloads and runs LLMs such as Llama, Gemma, Qwen and GPT-oss locally from Hugging Face, with full control and privacy. It can also connect to cloud models from OpenAI, Anthropic, Mistral, Groq and others, lets you create custom assistants, exposes an OpenAI-compatible API at localhost:1337 and supports the Model Context Protocol for agentic features. It is an open-source project on GitHub: https://github.com/janhq/jan.
How do I use Jan?
Download Jan for your OS from Jan.ai or GitHub Releases: Jan.exe, Jan.dmg, Jan.deb or Jan.AppImage; then open Jan and download a model such as Llama, Gemma or Qwen from Hugging Face; pick a model size your RAM can handle, for example 3B on an 8GB Mac. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is Jan for?
People who want a private ChatGPT-style app on their own computer, and developers who want a local OpenAI-compatible endpoint.
What can I do with Jan?
3 use cases so far, for example: Chat with an AI model fully offline; Use Jan as a local OpenAI-compatible API; Build Jan from source with your GPU engine. Each has steps and a copy-paste agent prompt.
What do I need to run Jan?
Windows 10+, macOS 13.6+ or most Linux distributions; RAM for the model size: 8GB for 3B models, 16GB for 7B, 32GB for 13B on macOS; To build from source: Node.js 20+, Yarn 4.5.3+, Make and Rust.
What are alternatives to Jan?
Other hot AI repos in Personal productivity: Cindy, Textgen, Learnharness, Chatbox, Planning with Files.
Is Jan safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.