LLM ReferenceLLM Reference

LFM2-24B-A2B

lfm-2-24b-a2b

Proprietary

About

LFM2-24B-A2B is the largest model in LiquidAI's LFM-2 hybrid-architecture family, designed for efficient on-device deployment with 24B total parameters and 2B active per token.

LFM2-24B-A2B has a 32K-token context window.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Rankings

Specifications

FamilyLFM-2
Released2025-11-01
Parameters24B
Context32K
Architecturemoe
Specializationgeneral
LicenseProprietary
Trainingpretrained

Created by

Adaptive and efficient AI models

Cambridge, MA, United States
Founded 2023
Website