Liquid AI 与 Hugging Face 发布 LFM2.5 系列 DSpark 草稿模型检查点，覆盖 1.2B、2.6B、8B-A1B 三款模型。其采用全新投机解码路径，不改变输出质量，大幅提升推理吞吐量。实测 GPU 端最高提速 3.18 倍，端侧设备也有明显加速。
8月5日，Liquid AI发布专为智能体工作流设计的26亿参数端侧模型LFM2.5-2.6B，可完全本地运行于手机等终端，提供低成本、低延迟与隐私保护方案。其基于34万亿词元预训练，词表容量128K，后训练融合监督微调、教师特化与多领域策略。
人工智能初创公司Liquid AI发布并开源了端侧大模型LFM2.5-8B-A1B，专为消费级硬件设计，优化工具调用和指令遵循能力。该模型采用稀疏混合专家架构，总参数量8.3B，但每个Token仅激活1.5B参数，在降低计算成本的同时提升推理性能，可流畅运行于手机和笔记本电脑上。
Liquid AI推出LFM2.5-1.2B-Thinking推理模型，拥有12亿参数，专为复杂逻辑推理和数学任务设计。该模型在端侧部署上实现突破，仅占用约900MB内存，可在现代手机上完全离线运行，将两年前需数据中心支持的推理能力成功迁移至个人移动设备。
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
VIP会员
