barozp/gemma-4-19b-a4b-it-REAP-GGUF
Same weights, converted vs 0xSero/Gemma-4-19B. Same weights stored in another dtype (BF16 → BF16/F32), plus 151 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/271, MLP 0/90, other 0/30, Attention 0/115
Same weights, converted vs 0xSero/Gemma-4-19B. Same weights stored in another dtype (BF16 → BF16/F32), plus 151 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/271, MLP 0/90, other 0/30, Attention 0/115