PulseAugur
实时 02:04:15
English(EN) One Open Source Project a Day (No. 166): Needle 2 — A 14 MB On-Device Tool-Calling Model

Cactus Compute发布14MB的Needle 2模型,用于设备端工具调用

Cactus Compute发布了Needle 2,这是一款专为工具调用任务设计的紧凑型设备端语言模型。该模型大小为14MB,量化为CQ2位,需要固定的28MB RAM,并采用了Simple Attention Network架构。其目标是在智能手机和可穿戴设备等设备上实现高效的AI部署,在工具调用基准测试中可媲美FunctionGemma 270M等更大模型的性能。该模型已在可穿戴设备的语音助手和结构化数据提取等场景中投入生产使用。 AI

影响 使资源受限的设备上能够运行更强大的AI应用,减少特定任务对云端推理的依赖。

排序理由 这是一个专业AI工具的发布,而非来自主要实验室的前沿模型发布。

在 dev.to — LLM tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Cactus Compute发布14MB的Needle 2模型,用于设备端工具调用

本文如何被排名

Signal score
38 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
这是一个专业AI工具的发布,而非来自主要实验室的前沿模型发布。
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, infra
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.

完整方法见我们的编辑标准

报道来源 [1]

  1. dev.to — LLM tag TIER_1 English(EN) · WonderLab ·

    每日一个开源项目(第166期):Needle 2 — 14MB的端侧工具调用模型

    <h2> Introduction </h2> <blockquote> <p>"The 2-bit model you deploy is the model that was trained."</p> </blockquote> <p>This is the <strong>166th</strong> article in the "One Open Source Project a Day" series. Today's project is <strong>Needle 2</strong>.</p> <p>On-device deploy…