mradermacher/MakeGemma3-abliterated-Improved-GGUF
Quantization (fewer layers) vs Testament200156/MakeGemma3-abliterated-Improved. mradermacher/MakeGemma3-abliterated-Improved-GGUF matches part of Testament200156/MakeGemma3-abliterated-Improved (809 of its 1248 tensors; the rest of Testament200156/MakeGemma3-abliterated-Improved has no counterpart). On the shared part: mradermacher/MakeGemma3-abliterated-Improved-GGUF is a GGUF quantization (Q8_0) of the same weights: 373 tensors match exactly and 436 within quantization error.
Tensors changed: Embeddings 0/1, lm_head 0/1, Norms 0/373, MLP 0/186, Attention 0/248