mradermacher/gemma-4-E4B-it-mentalchat16k-GGUF

Same weights, converted (fewer layers) vs howardbaik/gemma-4-E4B-it-mentalchat16k. mradermacher/gemma-4-E4B-it-mentalchat16k-GGUF matches part of howardbaik/gemma-4-E4B-it-mentalchat16k (623 of its 2076 tensors; the rest of howardbaik/gemma-4-E4B-it-mentalchat16k 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 0/278, MLP 0/126, other 0/85, Attention 0/132

On the Hub · Downloads on Model Pulse