Unverified50% confidenceFactExact time
Liquid AI开源了LFM2.5模型，总参数量为8.3B，每次推理只激活1.5B参数（约18%）
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
LFM2.5本地部署实测：8B参数碾压GPT-o3s的工具调用能力
bilibiliAGI_Ananas6/1/2026
Related Claims
UnverifiedLiquid探索的液态基础模型（LFM）基于常微分方程（ODE）的连续时间动态系统建模序列关系，在长序列推理时内存占用为线性而非平方复杂度67% similarUnverifiedThe LLaMA series of open-source models starts at 7B parameters64% similarVerified混合专家架构MoE通过稀疏激活机制，推理时只激活模型总参数的1/8至1/463% similarUnverifiedLLM-as-Compiler模式让AI只在初始阶段参与逻辑生成，代码确认后执行完全脱离大模型概率推理，与LLM-as-Runtime模式相对60% similarUnverifiedIn OpenAI's model naming system, minor version numbers (such as 5.3 to 5.5) typically represent fine-tuning optimizations on the same architecture, including RLHF strategy adjustments, inference efficiency improvements, or output style calibration.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/49055API
curl https://kongchang.com/api/v1/knowledge/claims/49055MCP
get_claim(id=49055)