Dev Radar
Support
LiveUpdated 2026-09-19 18:39 UTC

We release Needle 3: A Sliceable 8-29MB automation foundation model that can match…

We release Needle 3: A Sliceable 8-29MB automation foundation model that can match DeepSeek V4 Flash. One set of…

This is a dev post classified by Jev as Other (a launch), kept by the Dev Radar because it carries real work, not commentary.

We release Needle 3: A Sliceable 8-29MB automation foundation model that can match DeepSeek V4 Flash. One set of weights, every depth from 2 to 20 layers a model of its own, 25-121M parameters at CQ2-bit, built on our Simple Attention Networks and running locally at up to 4k tokens/sec decode speed on a Raspberry Pi 5. Needle does not chat. Every turn is a function call: give it the tools your app exposes and it picks the right ones and fills every argument from what the user said, or hand it a schema and it returns a typed record. Ask for something no tool covers and you get an empty list,

Posted by Cactus Compute (2.9k followers) 1 days ago · 2.8k likes · 385k views · view the original post on X. Kept by the Dev Radar as Other. Tools mentioned: Cactus Compute.

More dev work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:39 UTC. Full method.