bartowski/magnum-v4-22b-GGUF
Same weights, converted vs anthracite-org/magnum-v4-22b. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/168, Attention 0/224, lm_head 0/1
Same weights, converted vs anthracite-org/magnum-v4-22b. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/168, Attention 0/224, lm_head 0/1