conv.

← The whole story
AI
Cactus releases Needle 3, 8-29MB models for on-device tool calling

Cactus releases Needle 3 with intelligence laddering architecture

1 Sep 18 · 9d ago · 1 article · 1 post · 2 sources · development 1 of 7

Cactus Compute announced Needle 3, an 8-29 MB foundation model built on Simple Attention Network that supports tool calling and structured JSON output. The model uses intelligence laddering—each layer a sub-network with monotonically increasing capacity—allowing developers to choose from 2-20 layer configurations. The 4-layer variant, when fine-tuned on downstream tasks for one epoch, matches DeepSeek V4 Flash performance.

“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).”

Cactus Compute

Cactus Compute AI model developerHenry Ndubuaku Founder, CactusDeepSeek Competing model vendor (V4 Flash)

The whole story articlespostscomments the bright band is this development · numbered dots are the others · click one to jump

Peak 7 pieces in 3h at Sep 18, 12 PM; 26 pieces over 10 days (2 articles · 5 posts · 19 comments) Sep 17, 3 PM — 1 piece · 1 post — X 1Sep 17, 6 PM — 3 pieces · 2 articles · 1 post — Newswires 2, Hacker News 1Sep 17, 9 PM — quietSep 18, 12 AM — quietSep 18, 3 AM — quietSep 18, 6 AM — quietSep 18, 9 AM — 3 pieces · 2 posts · 1 comment — Mastodon 2, Hacker News 1Sep 18, 12 PM — 7 pieces · 7 comments — Hacker News 7Sep 18, 3 PM — 7 pieces · 1 post · 6 comments — Hacker News 6, Mastodon 1Sep 18, 6 PM — 2 pieces · 2 comments — Hacker News 2Sep 18, 9 PM — 1 piece · 1 comment — Hacker News 1Sep 19, 12 AM — quietSep 19, 3 AM — 1 piece · 1 comment — Hacker News 1Sep 19, 6 AM — quietSep 19, 9 AM — quietSep 19, 12 PM — quietSep 19, 3 PM — quietSep 19, 6 PM — 1 piece · 1 comment — Hacker News 1Sep 19, 9 PM — quietSep 20, 12 AM — quietSep 20, 3 AM — quietSep 20, 6 AM — quietSep 20, 9 AM — quietSep 20, 12 PM — quietSep 20, 3 PM — quietSep 20, 6 PM — quietSep 20, 9 PM — quietSep 21, 12 AM — quietSep 21, 3 AM — quietSep 21, 6 AM — quietSep 21, 9 AM — quietSep 21, 12 PM — quietSep 21, 3 PM — quietSep 21, 6 PM — quietSep 21, 9 PM — quietSep 22, 12 AM — quietSep 22, 3 AM — quietSep 22, 6 AM — quietSep 22, 9 AM — quietSep 22, 12 PM — quietSep 22, 3 PM — quietSep 22, 6 PM — quietSep 22, 9 PM — quietSep 23, 12 AM — quietSep 23, 3 AM — quietSep 23, 6 AM — quietSep 23, 9 AM — quietSep 23, 12 PM — quietSep 23, 3 PM — quietSep 23, 6 PM — quietSep 23, 9 PM — quietSep 24, 12 AM — quietSep 24, 3 AM — quietSep 24, 6 AM — quietSep 24, 9 AM — quietSep 24, 12 PM — quietSep 24, 3 PM — quietSep 24, 6 PM — quietSep 24, 9 PM — quietSep 25, 12 AM — quietSep 25, 3 AM — quietSep 25, 6 AM — quietSep 25, 9 AM — quietSep 25, 12 PM — quietSep 25, 3 PM — quietSep 25, 6 PM — quietSep 25, 9 PM — quietYesterday, 12 AM — quietYesterday, 3 AM — quietYesterday, 6 AM — quietYesterday, 9 AM — quietYesterday, 12 PM — quietYesterday, 3 PM — quietYesterday, 6 PM — quietYesterday, 9 PM — quietToday, 12 AM — quietToday, 3 AM — quietToday, 6 AM — quietToday, 9 AM — quietToday, 12 PM — quiet 12–7
1Cactus releases Needle 3 with…2–7Positive feedback on use case potential…
Sep 18Sep 19Sep 20Sep 21Sep 22Sep 23Sep 24Sep 25yesterdaynow · 3:49 PM ET

What was reported 1 claim about this development

  1. 2 outlets Show HN: Cactus Needle 3: 8-29MB automation models can match DeepSeek V4 Flash

    first by HN Best, 9d ago · also HN Frontpage

All 7 developments of Cactus releases Needle 3, 8-29MB models for on-device tool… →

Hacker NewsMastodonNewswiresX