Changelog

Jan v0.6.6: Enhanced llama.cpp integration and smarter model management

Major llama.cpp improvements, Hugging Face provider support, and refined MCP experience

Jan v0.6.5 brings responsive UI and MCP examples!

New MCP examples, updated pages, and bug fixes!

Jan v0.6.3 brings new features and models!

Unlocking MCP for everyone and bringing our latest model to Jan!

Jan v0.6.1 is here: It's a whole new vibe!

Are you ready for the sexiest UI ever?

Jan v0.6.5: MCP Revolution - Connect AI to Everything

Introducing Model Context Protocol support, browser automation, and powerful tool integrations

Jan v0.6.4: Performance Powerhouse

Massive speed improvements, GPU optimization, and streamlined model management

Qwen3 support is now more reliable.

Jan v0.5.17 is out: Qwen3 support is now more reliable

Jan Mobile: AI in Your Pocket

Introducing Jan Mobile - full-featured AI assistant for iOS and Android with cloud sync

Security fixes and UI improvements

Jan v0.5.16 is out: Security fixes and major improvements to Model Hub and chat experience

Jan v0.6.3: UI Renaissance

Complete interface redesign with improved UX, dark mode, and accessibility features

You can now tweak llama.cpp settings, and add any cloud model!

Jan v0.5.15 is out: Advanced llama.cpp settings and cloud model support

Jan Enterprise: Security & Compliance

Enterprise-grade security features, compliance tools, and team management capabilities

Run DeepSeek R1 Distills error-free!

Jan v0.5.14 is out: Run DeepSeek R1 Distills error-free!

A few key issues have been solved!

Jan v0.5.13 is here: A few key issues have been solved.

Jan gives you full control over your privacy

Improved Privacy settings to give full control over analytics

Jan v0.5.11 is here!

Critical issues fixed, Mac installation updated.

Jan v0.5.10 is live

Jan is faster, smoother, and more reliable.

Model downloads & running issues fixed

Jan v0.5.9 is here: fixing what needed fixing.

Jan supports Qwen2.5-Coder 14B & 32B

Jan v0.5.8 is out: Jan supports Qwen2.5-Coder 14B & 32B through Cortex

Jan has Stable, Beta and Nightly versions

This release is mostly focused on bug fixes.

Jan is more stable 👋

Jan supports Llama 3.2 and Qwen 2.5

Jan is faster now

Jan has faster CPU inference.

v0.5.3 is out with stability improvements!

You can run Llama 3.1 and Gemma 2 in Jan

Jan supports Claude 3.5 Sonnet

You can run Claude 3.5 Sonnet in Jan

Jan supports NVIDIA NIM

Jan has integrated NVIDIA NIM and supports Qwen 2 7B

New UI & Codestral Support

Revamped Jan's UI to make it clearer and more user-friendly

Jan now compatible with Aya 23 8B & 35B and Phi-3-Medium

Jan now supports Cohere's Aya 23 8B & 35B and Microsoft's Phi-3-Medium.

Jan now supports more GGUF models

We rebased to llamacpp b2865.

Jan now supports Llama3 and Command R+

Jan has added compatibility with Llama3 & Command R+

New Mistral Extension

Jan has a new Mistral Extension letting you chat with larger Mistral models via Mistral API

Groq API Integration

Nitro-Tensorrt-LLM Extension

Import models directly using the UI

Run Jan on your home-servers with Helm

Jan Data Folder

Local API server

Thread settings options in the right panel

Faster inference across: Mac, Windows, Linux, and GPUs