24B / 2.3B active (MoE)
LFM Open License v1.0
Largest LFM2 model at release; sparse Mixture-of-Experts architecture with 24B total parameters and ~2.3B active per token; hybrid backbone combining gated short convolutions with grouped-query attention (40 layers total: 30 conv + 10 attention) and top-4 routing across 64 experts per MoE block; designed to fit in ~32GB RAM for deployment on consumer laptops/desktops and edge hardware; 32,768 context window; day-zero inference support across llama.cpp, vLLM, and SGLang with GGUF quantization options; benchmark reports show log-linear quality scaling across GPQA Diamond, MMLU-Pro, IFEval, IFBench, GSM8K, and MATH-500 as the LFM2 family scales up