Krasnopjorovs/gemma-4-31b-it-Imatrix-IQ4_XS-GGUF

Quantization (fewer layers) vs google/gemma-4-31B-it. Krasnopjorovs/gemma-4-31b-it-Imatrix-IQ4_XS-GGUF matches part of google/gemma-4-31B-it (772 of its 1188 tensors; the rest of google/gemma-4-31B-it has no counterpart). On the shared part: Krasnopjorovs/gemma-4-31b-it-Imatrix-IQ4_XS-GGUF is a GGUF quantization (IQ4_XS) 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