PulseAugur
实时 21:13:20
日本語(JA) スマホで27B級LLMが動く!PrismMLが「Bonsai 27B」を無料公開 https:// pc.watch.impress.co.jp/docs/ne ws/2125273.html # impress # 市場 # AI # その他

PrismML的Bonsai 27B模型可在iPhone上运行,效率有所提升

PrismML发布了Bonsai 27B,一个拥有270亿参数的AI模型,可以在iPhone 17 Pro等移动设备上运行,仅需3.9GB内存。该模型的一个1位变体因其效率而受到关注,但据报道与Qwen 3.627B基线相比性能有所下降。 AI

影响 使更强大的AI模型能够直接在移动设备上运行,可能提高可访问性和离线能力。

排序理由 前沿实验室模型发布,附带系统卡。[lever_c_demoted from frontier_release: ic=2 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

PrismML的Bonsai 27B模型可在iPhone上运行,效率有所提升

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
前沿实验室模型发布,附带系统卡。[lever_c_demoted from frontier_release: ic=2 ai=1.0]
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
46 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准

报道来源 [3]

  1. Mastodon — mastodon.social TIER_1 日本語(JA) · [email protected] ·

    27B级大模型可在智能手机上运行!PrismML免费发布“Bonsai 27B” https:// pc.watch.impress.co.jp/docs/ne ws/2125273.html # impress # market # AI # Other

    スマホで27B級LLMが動く!PrismMLが「Bonsai 27B」を無料公開 https:// pc.watch.impress.co.jp/docs/ne ws/2125273.html # impress # 市場 # AI # その他

  2. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    PrismML 的 Bonsai 27B 因在 iPhone 17 Pro 上仅用 3.9 GB 运行 27B 级 AI 模型而成为头条新闻。然而,我们的分析表明 1 位变体 su

    PrismML's Bonsai 27B is making headlines for running a 27B-class AI model on an iPhone 17 Pro with just 3.9 GB. However, our analysis shows the 1-bit variant suffers a 9-point performance drop from the Qwen 3.627B baseline. Understand the compromises of mobile-first LLMs. https:/…

  3. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Bonsai 27B (1位大语言模型): 首个可在手机上运行的270亿参数级别模型 https://prismml.com/news/bonsai-27b # HackerNews # Tech # AI

    Bonsai 27B (1-bit LLM): The First 27B-Class Model to Run on a Phone https://prismml.com/news/bonsai-27b # HackerNews # Tech # AI