jkim96/gemma-4-E4B-it-DASHQ-Q2-GGUF

Quantization (fewer layers) vs google/gemma-4-E4B-it. jkim96/gemma-4-E4B-it-DASHQ-Q2-GGUF matches part of google/gemma-4-E4B-it (677 of its 2130 tensors; the rest of google/gemma-4-E4B-it has no counterpart). On the shared part: jkim96/gemma-4-E4B-it-DASHQ-Q2-GGUF is a GGUF quantization (IQ2_M) of the same weights: 296 tensors match exactly and 381 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