mradermacher/ablation-196-finalsft2-shisa-v2-gemma3-27b-GGUF
Quantization (fewer layers) vs shisa-ai/ablation-196-finalsft2-shisa-v2-gemma3-27b. mradermacher/ablation-196-finalsft2-shisa-v2-gemma3-27b-GGUF matches part of shisa-ai/ablation-196-finalsft2-shisa-v2-gemma3-27b (808 of its 1247 tensors; the rest of shisa-ai/ablation-196-finalsft2-shisa-v2-gemma3-27b has no counterpart). On the shared part: mradermacher/ablation-196-finalsft2-shisa-v2-gemma3-27b-GGUF is a GGUF quantization (Q8_0) of the same weights: 373 tensors match exactly and 435 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/373, MLP 0/186, Attention 0/248