BrainboxAI/code-il-E4B

Quantization (fewer layers) vs unsloth/gemma-4-E4B-it. BrainboxAI/code-il-E4B matches part of unsloth/gemma-4-E4B-it (677 of its 2130 tensors; the rest of unsloth/gemma-4-E4B-it has no counterpart). On the shared part: BrainboxAI/code-il-E4B is a GGUF quantization (Q4_K_M) 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