ReadyArt/Nimbz_Gemma-4-Dark-Gemistry-31B-GGUF

Quantization (fewer layers) vs Nimbz/Gemma-4-Dark-Gemistry-31B. ReadyArt/Nimbz_Gemma-4-Dark-Gemistry-31B-GGUF matches part of Nimbz/Gemma-4-Dark-Gemistry-31B (773 of its 1189 tensors; the rest of Nimbz/Gemma-4-Dark-Gemistry-31B has no counterpart). On the shared part: ReadyArt/Nimbz_Gemma-4-Dark-Gemistry-31B-GGUF is a GGUF quantization (Q8_0) of the same weights: 423 tensors match exactly and 350 within quantization error.

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

On the Hub · Downloads on Model Pulse