FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6-GGUF
Same weights, converted vs FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/2, other 0/20, MLP 0/48, Norms 0/44, Attention 0/24