bartowski/K2-Horizon-32B-GGUF
Same weights, converted vs IFM/K2-Horizon-32B. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Norms 0/129, MLP 0/192, Attention 0/256, lm_head 0/1, Embeddings 0/1
Same weights, converted vs IFM/K2-Horizon-32B. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Norms 0/129, MLP 0/192, Attention 0/256, lm_head 0/1, Embeddings 0/1