mradermacher/Gemma-4-31B-StyleTune-GGUF

Quantization (fewer layers) vs Gryphe/Gemma-4-31B-StyleTune. mradermacher/Gemma-4-31B-StyleTune-GGUF matches part of Gryphe/Gemma-4-31B-StyleTune (773 of its 1189 tensors; the rest of Gryphe/Gemma-4-31B-StyleTune has no counterpart). On the shared part: mradermacher/Gemma-4-31B-StyleTune-GGUF is a GGUF quantization (Q8_0) of the same weights: 361 tensors match exactly and 412 within quantization error.

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

On the Hub · Downloads on Model Pulse