Expired50% confidenceFactExact time
LFM2.5 uses a Mixture of Experts (MOE) architecture combined with Liquid convolution
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
LFM2.5 Local Deployment Hands-On: An 8B Parameter Model That Outperforms GPT-o3s in Tool Calling
bilibiliAGI_Ananas6/1/2026
Related Claims
UnverifiedLiquid AI first publicly introduced liquid convolution technology in LFM1.077% similarUnverifiedLFM2.5 has 24 layers total, with 18 using Liquid AI's proprietary LIV (Liquid) convolution and only 6 retaining traditional attention mechanisms69% similarUnverifiedLFM2.5-8B-A1B在工具调用（tool calling）场景中官方声称可达到4倍体量模型的效果61% similarUnverifiedL2约简成为后续fplll等高性能格约简库的理论基石59% similarVerifiedZhipu AI has released GLM 4.6, optimized with a Mixture of Experts (MoE) architecture.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/47922API
curl https://kongchang.com/api/v1/knowledge/claims/47922MCP
get_claim(id=47922)