nowfound

Work · June 17, 2025

Jan-nano, 4B agentic model that outperforms DeepSeek-v3-671B using MCP

We’ve been experimenting with how far a tiny model can go when it’s good at calling external tools - and have just released Jan-nano, a 4 B model trained for MCP. Jan-nano: - tops DeepSeek-V3-671B on MCP tool-use (SimpleQA 80.7%) - handles live web search and multi-step deep research - runs fully on-device (≈4GB VRAM) Tech notes - Base: Qwen3-4B - Fine-tuning: DAPO - We're going to release the full technical report soon Links - Demo tweet: https://x.com/menloresearch/status/1934809407604576559 - Model + GGUF:…

Jan-nano, 4B agentic model that outperforms DeepSeek-v3-671B using MCP launched on June 17, 2025 with 6 votes and more than 75% of that year's launches. The site was still online in September 2026, 1 year on.

What it does

Meet Jan-nano, a 4B model that outscores DeepSeek-v3-671B using MCP. It's built on Qwen3-4B with DAPO fine-tuning, it handles: - real-time web search - deep research Model + GGUF: https://t.co/i8KSXcDhA9 To run it locally: - Install Jan Beta: https://t.co/l5UMY52zfc - Download Jan-nano in Jan Hu…

In the maker’s words, at launch

We’ve been experimenting with how far a tiny model can go when it’s good at calling external tools - and have just released Jan-nano, a 4 B model trained for MCP. Jan-nano: - tops DeepSeek-V3-671B on MCP tool-use (SimpleQA 80.7%) - handles live web search and multi-step deep research - runs fully on-device (≈4GB…

Does a similar job

all alternatives →
  • GPT-4.1 in the API2025 · openai.com · ▲375

    Announcing GPT-4.1, GPT-4.1 mini, & GPT-4.1 nano in the API

  • GPT‑5.4 mini and nanoMar 2026 · openai.com · ▲267

    Fast and efficient models optimized for coding and subagents

  • Janus2025 · github.com · ▲224

    Unified Multi-Modal AI by DeepSeek

  • DeepSeek-V4Apr 2026 · huggingface.co · ▲387

    The open-source era of 1M context intelligence

  • Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try itJul 2026 · ctgt.ai · ▲170

    We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. With V4 as the teacher though, we realized it would be timely to measure if the censorship characteristic of it transferred to the distilled version of the base model. tl;dr it didn't, the teacher answered politically sensitive questions 7 SDs differently than expected, but the distilled model's…

  • DSH Desktop24d ago · deepseek.com · ▲176

    Official app for DeepSeek’s open-source agent harness

More work this month

the category →

Source: Show HN post ↗ · launch text quoted in part

Launched alongside, June 2025

the whole month →
  • IM

    Hey HN! Pilots everywhere are required to keep a logbook of all their flying hours, aircraft, airports, and so on. Since I track everything digitally (some people still just use paper logbooks!), I put together some data visualizations and a few 3D globes to show my flying history. This globe is probably my favourite so far: https://jameshard.ing/pilot/globes/all If you’ve got ideas for other graphs or ways to show this kind of data, I’d love to hear them!

    Life & fun · 2025 · jameshard.ing

  • Stunning presentations with AI. No design skills required.

    AI · 2025 · chroniclehq.com

  • Build native mobile apps for iOS and Android without code.

    Dev tools · 2025 · bble.io

  • Twenty▲989

    Build your Enterprise CRM with an AI-friendly SDK

    Dev tools · 2025 · twenty.com

  • All your connections, across all your socials.

    AI · 2025 · pally.com

  • I was the main contributor to workout.lol, an open-source fitness app to easily build a workout routine. The project had traction (1.4k GitHub stars, 95 forks, ~20K visits/month), but was eventually sold due to video licensing hurdles. The new owner stopped maintaining it, and the repo went abandoned. Over the next 9 months, I sent 15 emails to try to save it : no replies. Feature requests & issues were ignored. The community was left with a "broken" tool let's say. I couldn't just let it die So I built the new version from scratch with the same open-source spirit, but a better…

    Dev tools · 2025 · github.com