← Latest products

Cactus Needle 3

8-29MB automation models can match DeepSeek V4 Flash. A foundation model for mobile, wearables, robots, smart home, automotive and microcontrollers. One 8-29 MB binary that beats models 10x its size on mobile tool calls and matches 2-3x bigger models on extraction. We submitted Needle 2 here a few weeks ago, and the feedback in the discussion thread was incredibly valuable, thanks!

Visit cactuscompute.comexternal site

Reactions (2)

Similar products

by description similarity

  1. Needle

    github.com

    We Distilled Gemini Tool Calling into a 26M Model

    Hacker News776 pts

  2. I shrank DeepSeek V4 Flash to 57GB and it wrote a compiler on my Mac

    huggingface.co

    Text Generation model. Download, explore files and run it on Hugging Face.

    Hacker News21 pts

  3. Warp

    github.com

    Run DeepSeek v4.1 Flash with 5 GB of RAM at 3.77 tok/s

    Hacker News16 pts

  4. Cactus

    github.com

    Ollama for Smartphones

    Hacker News231 pts

  5. 80% faster

    github.com

    50% less memory, 0% loss of accuracy Llama finetuning

    Hacker News385 pts