majentik/gemma-4-E4B-RotorQuant-GGUF-Q8_0

Quantization (fewer layers) vs google/gemma-4-E4B. majentik/gemma-4-E4B-RotorQuant-GGUF-Q8_0 matches part of google/gemma-4-E4B (677 of its 2130 tensors; the rest of google/gemma-4-E4B has no counterpart). On the shared part: majentik/gemma-4-E4B-RotorQuant-GGUF-Q8_0 is a GGUF quantization (Q8_0) of the same weights: 297 tensors match exactly and 380 within quantization error.

Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168

On the Hub · Downloads on Model Pulse