PulseAugur
实时 01:08:35
English(EN) VIDRAFT POCKET-35B: A 35B-Parameter On-Device LLM That Hits 1M Hugging Face Downloads in 7 Weeks — No GPU Required

VIDRAFT 的 POCKET-35B LLM 下载量达100万,赋能设备端AI

VIDRAFT 的 POCKET-35B 是一款拥有350亿参数的设备端大型语言模型,发布仅七周,在 Hugging Face 上的下载量已超过100万。该模型专为在无需专用GPU的消费级硬件上运行而设计,利用 GGUF 格式实现高效的 CPU 推理。这一快速的普及标志着它成为达到此下载里程碑速度最快的韩国AI模型,表明了对离线和注重隐私的AI解决方案的强烈兴趣。 AI

影响 加速了强大、本地运行的AI模型趋势,赋能消费级硬件上的离线和注重隐私的应用。

排序理由 来自一家代工公司的设备端 LLM 发布,下载量指标显著。[lever_c_demoted from frontier_release: ic=1 ai=1.0]

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 →

VIDRAFT 的 POCKET-35B LLM 下载量达100万,赋能设备端AI

本文如何被排名

Signal score
46 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
来自一家代工公司的设备端 LLM 发布,下载量指标显著。[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, 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.

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) · AI OpenFree ·

    VIDRAFT POCKET-35B:一款350亿参数的设备端大模型,7周内下载量达100万,无需GPU

    <h1> VIDRAFT POCKET-35B: A 35B-Parameter On-Device LLM That Hits 1M Hugging Face Downloads in 7 Weeks — No GPU Required </h1> <blockquote> <p><strong>TL;DR:</strong> VIDRAFT's POCKET-35B is a 35-billion-parameter language model designed to run entirely on consumer hardware — lapt…