Skip to content

Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots

8.5 relevance
Score Breakdown
technical depth
8
novelty
9
actionability
8
community
9
strategic
8
personal
10

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

14MB agentic LLM for edge devices, a groundbreaking open-source project directly matching the reader's interests in AI agents and platform engineering.

AI/ML cactuscompute.com
Cactus - On-device AI for Smartphones, Laptops & Edge
Summary

The discussion is nascent due to no comments yet, but the post introduces Needle2, a 14MB agentic LLM optimized for edge devices like phones, wearables, and robots, achieving 500 tokens/sec on a Raspberry Pi 5 with 45M parameters at 2-bit compression. The community has not yet weighed in, but the original post highlights significant improvements from user feedback on the first version.