mradermacher/gemma-4-31BHERETIC-Thinking-GGUF

Quantization (fewer layers) vs mirxa2/gemma-4-31BHERETIC-Thinking. mradermacher/gemma-4-31BHERETIC-Thinking-GGUF matches part of mirxa2/gemma-4-31BHERETIC-Thinking (772 of its 1188 tensors; the rest of mirxa2/gemma-4-31BHERETIC-Thinking has no counterpart). On the shared part: mradermacher/gemma-4-31BHERETIC-Thinking-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