helenk/gemma-4-E4B-finetune-GGUF

Quantization (fewer layers) vs unsloth/gemma-4-E4B-it. helenk/gemma-4-E4B-finetune-GGUF matches part of unsloth/gemma-4-E4B-it (623 of its 2130 tensors; the rest of unsloth/gemma-4-E4B-it has no counterpart). On the shared part: helenk/gemma-4-E4B-finetune-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 279 tensors match exactly and 344 within quantization error.

Tensors changed: Embeddings 0/2, Norms 0/278, MLP 0/126, other 0/85, Attention 0/132

On the Hub · Downloads on Model Pulse