Show HN: Cactus Needle 3: 8-29MB automation models can match DeepSeek V4 Flash

In one line

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.

Opening excerpt

One set of weights, every depth from 2 to 20 layers a model of its own: an intelligence ladder.

Tool calls Given the functions your app exposes, Needle picks the right ones and fills every argument from what the user said. Ask for two things and you get two calls in order; ask for something no tool covers and you get an empty list, not a guess. Structured extraction Declare a shape, hand over messy text, get typed fields back: an invoice, a booking, a notification, a form. The decode grammar guarantees the output parses. Extraction generalised well to classification problems too. Text embedding The same model returns a vector for a sentence, so an app can search, match and route locally: find the note you mean, pick the tool closest to a request, collapse duplicate alerts. What that looks like in a product:

Intelligence laddering. Every layer of Needle 3 is a sub-network with monotonically increasing capacity. Developers can choose the right size from the 2-layer (2L) subnetwork to 20 layers (20L).

(Excerpted from the original; full article via the source link below.)

This story hit the Hacker News front page today (137 points / 69 comments, via cactuscompute.com). Our Tech Radar aggregates daily signals on AI engineering, backend architecture and DevOps — browse the related services and further reading below, or get in touch with our team.