Coding · Free · collected from public sources
Visit Show HN: Cactus Needle 3: 8-29MB automation models can match DeepSeek V4 Flash ↗
Hey HN, Henry from Cactus here.<p>We submitted Needle 2 here a few weeks ago, and the feedback in the discussion thread was incredibly valuable, thanks! Thanks to all that feedback, we’ve been able to move quickly to release Needle 3 and I'd love to hear what you think again.<p>The key features:<p>1) Automation (tool calls & structured JSON output): Needle still doesn't chat by design, its quite challenging to pack general capacity into such small models, so we focus on tool calls and structured JSON. If no tool you declared fits the request, you get an empty list back (note for when playing with the demo).<p>2) Intelligence Laddering: Every layer (2 to 20) is a deployable subnetwork, so one set of weights, 25 to 121 million parameters at 2-bit, shipping as 8-29MB binaries. On a Raspberry Pi 5 it decodes at up to 4k tokens/sec and prefills at up to 10k.<p>3) Monarch Hadamard MLP: replaces the dense FFN with three learnable Walsh-Hadamard-initialized Kronecker (Monarc
ai hackernews show-hn
Listed as Free. Pricing changes often — confirm on the official site.
Listings are collected automatically from public sources and refreshed daily. We do not take payment for placement.