Liquid AI 持续推出小尺寸 VLM、Omni 与决策模型,可在 Llama 应用直接运行
如果你想在笔记本上跑多模态模型,Liquid AI 这波值得关注。VLM、Omni、决策模型三条线全是小尺寸,和 LFM 系列一样走端侧路线,直接在 Llama 应用就能调。做端侧或低成本部署的开发者可以试试。
Liquid AI 近期密集发布多类小参数模型,覆盖视觉语言模型(VLM)、全模态 Omni 模型以及决策模型三条产品线。推文作者 Merve Noyan 表示自己通过 Llama 应用使用 Liquid AI 发布的每一款模型,并称赞该团队让所有人都能在本地跑起小模型。
Liquid AI 的差异化在于坚持小尺寸路线:相比追求参数规模的大厂,其 VLM 处理图文输入、Omni 模型覆盖音视频等多模态、决策模型面向任务路由与选择场景,均可在消费级设备运行。对开发者而言,这类小模型降低了端侧部署和多模态试用的门槛,是 Hugging Face 生态中少数持续产出 tiny 级开源模型的玩家。
lately @liquidai is killing it with their small models out there, they release VLMs, Omni models as well as their decision models
I use anything and everything they release through @Llama_app very grateful there's a player releasing tiny models everyone can run 🤗 https://t.co/N5A3RCDMvw
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Liquid AI, LFM, multimodal, open-source models.
Source attribution: curated from Merve Noyan (@mervenoyann).