mradermacher/Gemma-4-26B-A4B-StyleTune-V2-GGUF

Quantization vs Gryphe/Gemma-4-26B-A4B-StyleTune-V2. mradermacher/Gemma-4-26B-A4B-StyleTune-V2-GGUF is a GGUF quantization (Q8_0) of the same weights: 301 tensors match exactly and 207 within quantization error.

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

On the Hub · Downloads on Model Pulse