PulseAugur
EN
LIVE 12:23:41
Français(FR) Needle 2 : un foundation model de 45M de paramètres pour le tool calling et l'extraction structurée, compressé en un seul binaire de 14MB tournant avec 28MB de

Needle 2: Tiny 14MB open-source model runs LLM tasks locally

Needle 2 is an open-source foundation model with 45 million parameters, designed for tool calling and structured data extraction. It is compressed into a single 14MB binary that can run locally on devices with as little as 28MB of RAM. This model is intended for use on mobile phones, wearables, and IoT devices, operating without reliance on cloud infrastructure. AI

IMPACT Enables on-device AI capabilities for wearables and IoT, reducing reliance on cloud processing.

RANK_REASON Release of a new open-source model with specific technical details. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — fosstodon.org →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Needle 2: Tiny 14MB open-source model runs LLM tasks locally

How we ranked this

Signal score
19 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Release of a new open-source model with specific technical details. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — fosstodon.org TIER_1 Français(FR) · [email protected] ·

    Needle 2: a 45M parameter foundation model for tool calling and structured extraction, compressed into a single 14MB binary running with 28MB of

    Needle 2 : un foundation model de 45M de paramètres pour le tool calling et l'extraction structurée, compressé en un seul binaire de 14MB tournant avec 28MB de RAM. Open source, pensé pour tourner en local sur téléphones, wearables et objets connectés, sans cloud. ⬇️ https:// git…