mradermacher/gemma-3-4b-it-heretic-GGUF

Same weights, converted (fewer layers) vs coder3101/gemma-3-4b-it-heretic. mradermacher/gemma-3-4b-it-heretic-GGUF matches part of coder3101/gemma-3-4b-it-heretic (444 of its 883 tensors; the rest of coder3101/gemma-3-4b-it-heretic has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse