mradermacher/gemma-4-E4B-it-uncensored-GGUF

Same weights, converted (fewer layers) vs InfinimindCreations/gemma-4-E4B-it-uncensored. mradermacher/gemma-4-E4B-it-uncensored-GGUF matches part of InfinimindCreations/gemma-4-E4B-it-uncensored (677 of its 2130 tensors; the rest of InfinimindCreations/gemma-4-E4B-it-uncensored has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 43 new tensors.

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

On the Hub · Downloads on Model Pulse