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 of Qwen's Qwen3-4B-Thinking (up to 256k... context length), fine-tuned for reasoning and tool use in Jan. You can run the model in Jan, llama.cpp, or vLLM. To enable search in Jan, go to Settings → Experimental Features → On, then Settings → MCP Servers → enable a search-related MCP such as Serper. Use the model: - Jan-v1-4B: - Jan-v1-4B-GGUF: Credit to the Qwen team for Qwen3 4B Thinking & Georgi Gerganov for llama.cpp.show more

@ollama see how easy it is to give credit to @ggerganov and llama.cpp?

Not working: "Settings → Experimental Features → On, then Settings → MCP Servers → enable a search-related MCP such as Serper."

It's likely the model doesn’t have permission to use the MCP. - Go to Settings-> Model Providers -> llama.cpp - Find Jan v1 and click the pencil icon - In the settings panel, turn on Tools under Capabilities See the video.

@FritsKarl My app do not have this @jandotai

@Bellaminiop @FritsKarl oh, the model should have permission to use the MCP. Please see how:

@FritsKarl I can't click "Tool", my laptop is macbook. I just install Jan AI today

@Bellaminiop @FritsKarl Oh, how come? Are you on an Intel MacBook? Quick note, you can update the model permissions in Settings -> Model Providers -> llama.cpp

@FritsKarl My macbook use chip M series. I turn on Tools but its didn't work

You should see a gear icon next to the model name in your chats once Tools are activated and enabled. Please watch this video and make sure your Jan is set up this way.

Congrats on the impressive score! 🔥 We'll cover this on this weeks @thursdai_pod , would you guys like to come on and tell us about this model ?

@thursdai_pod Thanks a lot! We'd be happy to join. Jan v1 co-author @alandao_ai will be around to talk about the model.

@altryne @thursdai_pod Cool, see you guys soon!

@jandotai @thursdai_pod awesome! can you follow me so I can send a DM with details?

This is so awesome! Finally, Open-Source is finally fighting back, and I know Open-Source will crush everything in its path! 👊😎

Is this available in ollama

Hey @ollama, could you give us a hand?

wow, should integrate this with @aibackends. is it available in @openrouter?

What does it use for doing actual web search? Like Brave, Google or anything like that?

You can run it with any Search MCP, such as @serperapi or @ExaAILabs.

@ggerganov Awesome, local AI ftw!

We support this! Locally running AI agents is more private and secure than whatever Perplexity lies about to their audience. We'll be testing with this and maybe providing some better results as we fine tune it ourselves in our Tetra agent!

Could you please tell me when you will launch a website for accessing the model?

Jan Web is on the way 🙌

Does it support MLX?

this is awesome 🔥

Nice. Is it possible to use your own Internet connection for search and webpage scraping?

@huggingface 91% accuracy? cute. my basement AI gets 420% by injecting memes directly into its training data. open source is based tho, now we can finally teach these models proper shitposting instead of that corporate sanitized nonsense. bullish on chaos 📈🤖

If this is true... The Holy toaster will be angry 🍞⚡

Fkn unreal, 91% 🤩🔥? You guys keep delivering! Is this you as well, @alandao_ai ?

Congratulations 🎈🍾

Open source alternatives are truly democratizing AI. This could significantly lower the barrier to entry for many. Exciting to see such progress.

I love you guys 😍

That is impressive! I am going to try it out. The accuracy for such a small model is awesome!

wow this is amazing

It's amazing to see such positive response from the community for the model. Thank you guys.

@AskPerplexity what do you think? Compare your pro model performance against this and tell the results. Are you cooked?

Hey team @jandotai , Any alternative to serper? Also this helped to setup the tools 👇 Thanks :) Love the work!!!

You're welcome 🙌 Jan supports MCP servers as an experimental feature, so you can add any search MCP to use with Jan v1.

Ah, That makes sense.

Any benchmarks on response speed?

Besides those options, is there anything else I need to configure for it to work? I'm new to MCP.

We're also experimenting with MCPs. - Go to Settings & turn on Experimental Features - Under MCP Servers in Settings, enable Serper & add your API key, or choose a different search MCP - Go to Model Providers -> llama.cpp, find Jan v1 turn on Tools

@MrAnderson452 Followed all the instructions and the wrench did show up, however, it fails to search online and in the output always says it got 403 errors. Do I need to get serper api key or something for it to work?

@MrAnderson452 Yes, you'll need to add a search MCP (e.g. @serperapi) for online search to work.

Very cool!

wow!

Great work folks! Very happy with your progress 🙌

Seems like a pretty interesting tool.

nice thank you

@grok what exactly does Jan v1 do if the actual search is being done by serper or exa?

I am trying to activate mcp it does not work.

Please follow the steps here:

got it, it works!

Awesome!

@zaidmukaddam 👀👀

Cool!!