Jan-nano is a model fine-tuned with DAPO on Qwen3-4B. Jan-nano comes with some unique capabilities:

  • It can perform deep research (with the right prompting)
  • It picks up relevant information effectively from search results
  • It uses tools efficiently

The model was evaluated using SimpleQA - a relatively straightforward benchmark to test whether the model can find and extract the right answers.

Jan-nano outperforms Deepseek-671B on this metric, using an agentic and tool-usage-based approach. A 4B model obviously has its limitations, but it’s interesting to see how far these things can be pushed. Jan-nano can serve as your self-hosted Perplexity alternative on a budget.

You can find the model at: https://huggingface.co/Menlo/Jan-nano

And a gguf is available at: https://huggingface.co/Menlo/Jan-nano-gguf

  • geneva_convenience@lemmy.ml
    2·
    2 days ago

    Very cool. This kind of stuff is interesting for local use on phones. Not that I will be implementing that myself. But someone will probably do so in the future and I will be using it