Expired95% confidenceEventExact time
Liquid AI团队发布了LFM2.5-8B-A1B模型，采用混合专家（MoE）架构
1
Sources
95%
Confidence
Medium-term (~90 days)
Relevance
5/28/2026
First Seen
Valid until: 8/26/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedLiquid AI has open-sourced the LFM2.5 model83% similarUnverifiedLiquid AI first publicly introduced liquid convolution technology in LFM1.075% similarUnverifiedLiquid AI has open-sourced the LFM2.5 model, which has a total of 8.3B parameters and activates only 1.5B parameters (approximately 18%) per inference.73% similarUnverifiedLFM2.5 uses a Mixture of Experts (MOE) architecture combined with Liquid convolution72% similarUnverifiedMistral AI's Mixtral 8x7B adopts a Mixture of Experts (MoE) architecture.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/623API
curl https://kongchang.com/api/v1/knowledge/claims/623MCP
get_claim(id=623)