Enerccio/gemma-4-31b-abliterated-GGUF

Quantization (fewer layers) vs Kooten/gemma-4-31b-abliterated-v1.1. Enerccio/gemma-4-31b-abliterated-GGUF matches part of Kooten/gemma-4-31b-abliterated-v1.1 (772 of its 1188 tensors; the rest of Kooten/gemma-4-31b-abliterated-v1.1 has no counterpart). On the shared part: Enerccio/gemma-4-31b-abliterated-GGUF is a GGUF quantization (Q8_0) of the same weights: 361 tensors match exactly and 411 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230

On the Hub · Downloads on Model Pulse