PulseAugur
中
实时 20:00:54
English(EN) Poolside Lagona S2.1 Review: A 118B MoE Coding Model That Runs on a Single 3090

Poolside AI 发布 Lagona S2.1,一款可在消费级硬件上运行的 118B MoE 编码模型

Poolside AI 发布了 Lagona S2.1,这是一款拥有 1180 亿参数的混合专家(MoE)模型,专为开发者的本地部署而设计。尽管参数量巨大,但每个 token 仅激活其中一小部分,使其能够运行在 RTX 3090 或 MacBook 等消费级硬件上。该模型在编码基准测试中表现强劲,超越了 Gemini 3.5 Flash 和 Claude Sonnet 等模型,并能够生成复杂的应用程序和模拟。 AI

影响 使开发者能够在本地运行强大的编码模型,可能提高生产力并减少对云基础设施的依赖。

排序理由 一家中型 AI 实验室发布的新模型,具有显著的效率和本地部署能力。[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 →

Poolside AI 发布 Lagona S2.1,一款可在消费级硬件上运行的 118B MoE 编码模型

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
一家中型 AI 实验室发布的新模型,具有显著的效率和本地部署能力。[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
107 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

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) · shakti tiwari ·

    Poolside Lagona S2.1 评测:一款可在单块 3090 上运行的 118B MoE 编码模型

    <p><a class="article-body-image-wrapper" href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fimages.unsplash.com%2Fphoto-1518770660439-4636190af475%3Fw%3D1200%26q%3D80"><img alt="Poolside Lagona S2.1 - local AI…