Unverified50% confidenceEventExact time
LiquidAI released the new LFM2.5-24B-A2B model.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
Related Entities
Related Claims
UnverifiedData released by Liquid AI shows that LFM2.5-24B-A2B beats Qwen3.6-35B-A3B on tool-use benchmarks69% similarUnverifiedLFM2.5-24B-A2B is a pure-text reasoning model with no vision tower, always begins with a <think> block, and those needing image capabilities should use LFM2.5-VL-3B (the highest model in the LFM2.5 VL series).65% similarUnverifiedvLLM v0.27.0 adds support for the K-EXAONE-2.0-750B-A37B large-scale MoE model.62% similarUnverifiedLFM2.5-24B-A2B and Qwen3.6-35B-A3B are both open-source, locally deployable MoE architecture models, with hardware requirements within the range of high-end consumer devices61% similarUnverifiedThe architecture of LFM2 (Liquid AI) is 10 gated short convolution blocks plus 6 GQA blocks, discovered through hardware-in-the-loop search rather than human design.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1038617API
curl https://kongchang.com/api/v1/knowledge/claims/1038617MCP
get_claim(id=1038617)