majentik/gemma-4-31B-RotorQuant-GGUF-Q4_K_M

Quantization (fewer layers) vs google/gemma-4-31B. majentik/gemma-4-31B-RotorQuant-GGUF-Q4_K_M matches part of google/gemma-4-31B (772 of its 1188 tensors; the rest of google/gemma-4-31B has no counterpart). On the shared part: majentik/gemma-4-31B-RotorQuant-GGUF-Q4_K_M is a GGUF quantization (Q4_K_M) 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