日本語(JA) 74Bが24GBに！ローカルAI向けNemotron 3.5 Bolt登場 https:// pc.watch.impress.co.jp/docs/ne ws/2148734.html # impress # 市場 # AI # その他

Nemotron 3.5 Bolt 发布，面向本地 AI 且尺寸缩小

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-16 04:40

新款 AI 模型 Nemotron 3.5 Bolt 已发布，专为本地 AI 应用进行了优化。该模型拥有 740 亿参数，但体积缩小至 24GB，使其更容易在设备上或本地部署。 AI

影响此次发布使得强大的 AI 模型更容易用于本地部署，有望加速设备端 AI 应用。

排序理由 Frontier-lab 模型发布，附带系统卡。[lever_c_demoted from frontier_release: ic=1 ai=1.0]

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

本文如何被排名

Signal score: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Significant; Frontier-lab 模型发布，附带系统卡。[lever_c_demoted from frontier_release: 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, 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。