blascotobasco/Gemma-4-96E-A4B-Heretic

Same weights, repacked vs coder3101/gemma-4-26B-A4B-it-heretic. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/4, Norms 0/433, other 0/62, MLP 0/171, Attention 0/223

3 derivatives checked

• mradermacher/Gemma-4-96E-A4B-Heretic-i1-GGUF: Quantization
• mradermacher/Gemma-4-96E-A4B-Heretic-GGUF: Quantization
• WaveCut/Gemma-4-96E-A4B-Heretic-TQ: Quantization

On the Hub · Downloads on Model Pulse