English(EN) Liquid AI has released LFM3, a family of six open-weight models of roughly 2B parameters built on one shared backbone, covering text, vision, audio, omni and de

Liquid AI 发布 LFM3 系列 20 亿参数多模态开放权重模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 02:52

Liquid AI 推出了 LFM3，这是一个新的系列，包含六个开放权重模型，每个模型约有 20 亿参数。这些模型共享通用架构，旨在处理包括文本、视觉、音频和决策在内的各种任务。据报道，表现最佳的模型 LFM3-1.7B 在 Liquid AI 的内部基准测试中优于 Qwen3.5-9B，并且在 4 位精度下仅需约 1 GB 内存即可高效运行。 AI

影响为研究人员和开发者提供了新的开放权重多模态模型，可能在文本、视觉和音频处理领域催生新的应用。

排序理由非前沿实验室发布新的开放权重模型家族。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

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: 2 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 非前沿实验室发布新的开放权重模型家族。[lever_c_demoted from research: 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

Mastodon — mastodon.social TIER_1 English(EN) · [email protected] · 2026-10-28 02:52

Liquid AI 发布 LFM3，一个拥有约 20 亿参数的六个开放权重模型家族，基于一个共享骨干构建，涵盖文本、视觉、音频、全能和去

Liquid AI has released LFM3, a family of six open-weight models of roughly 2B parameters built on one shared backbone, covering text, vision, audio, omni and decision tasks. The flagship LFM3-1.7B averages 49.37 across 29 benchmarks, ahead of Qwen3.5-9B on Liquid's own evaluation…

链接 marktechpost.com/…/liquid-ai-lfm3-open-we…

本文如何被排名

报道来源 [1]

Liquid AI 发布 LFM3，一个拥有约 20 亿参数的六个开放权重模型家族，基于一个共享骨干构建，涵盖文本、视觉、音频、全能和去

相关实体

相关话题