mradermacher/amoral-gemma3-4B-v2-GGUF
Same weights, converted (fewer layers) vs soob3123/amoral-gemma3-4B-v2. mradermacher/amoral-gemma3-4B-v2-GGUF matches part of soob3123/amoral-gemma3-4B-v2 (443 of its 883 tensors; the rest of soob3123/amoral-gemma3-4B-v2 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Norms 0/205, MLP 0/102, Attention 0/136