👋 Jan It works wonderfully, it has better performance, and it is rightly at the top on GitHub. The result that is seen is when I turn on the GPU integrated into the CPU and when it was off.

Open-source models can do Deep Research too. This video shows a full research report created by Jan-nano. To try it: - Get Jan-nano from Jan Hub - In settings, turn on MCP Servers and Serper API - Paste your Serper API key Your deep research assistant is ready.

BOOOM! transformers now has a baked-in http server w/ OpenAI spec compatible API Launch it with `transformers serve` and connect your favorite apps. Here I'm running 👋 Jan with local transformers and hot-swappable models. There is preliminary tool call support as well!

hey Jan, do something for me 🪄

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer

what a time to be alive: a local 4B model (Jan-nano) + Web Search tool is already amazing to get the info you need with no overhead 🚀

I'm glad to announce our latest research:🍎 Lucy. Lucy is a model trained specifically to optimize machine-generated task vectors. Let’s say you have a reasoning model where everything happens inside: <think>... etc ...</think> Essentially, the moment the <think> tag ends,

OK so . Node JS MCP servers do NOT work on LM Studio , I was able to get the momory/knowledge graph I use working with 👋 Jan . Only certain LLMs have tool use enabled on Jan though. Qwen 3 4B is pretty fast, but the addon also adds to inference time. TLDR: If you want to

Jan v0.6.6 is out: Jan now runs fully on llama.cpp. - Cortex is gone, local models now run on Georgi Gerganov's llama.cpp - Toggle between llama.cpp builds - Hugging Face added as a model provider - Hub enhanced - Images from MCPs render inline in chat Update Jan or grab the latest.

My app is on product hunt, help me vote :) producthunt.com/products/silk-…

👋 Jan running OpenAI 's GPT-OSS 120B on a Windows desktop with some layer offloaded to CPU. :)

Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro. In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally. Use cases: - Web search - Deep Research Built on the new version

Jan-V1-4B on Jan using llamacpp GGUF, perfect! I tested 4bit and 8bit quality of responses is amazing on both engine and quantizations! Here a quick video. Link to MLX models below. Enjoy this amazing small thinking LLM!

Automatically adjusts the height of the window 🤔 ChatGPT

Jan v0.6.8 is out: Jan is more stable now! - Stability fixes for model loading - Better llama.cpp: clearer errors & backend suggestions - Faster MoE models with CPU offload - Search private Hugging Face models - Custom Jinja templates Update your Jan or download the latest.

🫡

LMAO!

New logo for Vercel, thank me later!

Just in case.

Looking alternative Vercel! 🤡