noctrex/LFM2-24B-A2B-MXFP4_MOE-GGUF

Same weights, converted vs LiquidAI/LFM2-24B-A2B. Same weights stored in another dtype (BF16/F32 → MXFP4/F16), plus 152 new tensors.

Tensors changed: Embeddings 0/2, other 0/60, MLP 0/44, Norms 0/100, Attention 0/40

On the Hub · Downloads on Model Pulse