mradermacher/gemma-4-26b-a4b-heretic-styletune-v2-head-GGUF

Quantization vs jebcarter/gemma-4-26b-a4b-heretic-styletune-v2-head. mradermacher/gemma-4-26b-a4b-heretic-styletune-v2-head-GGUF is a GGUF quantization (Q8_0) of the same weights: 301 tensors match exactly and 207 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/271, MLP 0/90, other 0/30, Attention 0/115, lm_head 0/1

On the Hub · Downloads on Model Pulse