mhndayesh/gemma-4-E2B-offsec-expert-GGUF

Quantization vs lmstudio-community/gemma-4-E2B-it-GGUF. mhndayesh/gemma-4-E2B-offsec-expert-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 284 tensors match exactly and 317 within quantization error.

Tensors changed: Norms 0/247, other 0/109, Attention 0/140, MLP 0/105

On the Hub · Downloads on Model Pulse