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

Quantization (fewer layers) vs Ateron/Gemma-4-AssGuard-31B. mradermacher/Gemma-4-AssGuard-31B-GGUF matches part of Ateron/Gemma-4-AssGuard-31B (772 of its 1188 tensors; the rest of Ateron/Gemma-4-AssGuard-31B has no counterpart). On the shared part: mradermacher/Gemma-4-AssGuard-31B-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