mradermacher/Gemma-3n-4b-Vision-Finetuned-GGUF

Same weights, converted (fewer layers) vs Aasher/Gemma-3n-4b-Vision-Finetuned. mradermacher/Gemma-3n-4b-Vision-Finetuned-GGUF matches part of Aasher/Gemma-3n-4b-Vision-Finetuned (809 of its 1676 tensors; the rest of Aasher/Gemma-3n-4b-Vision-Finetuned has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 37 new tensors.

Tensors changed: Embeddings 0/1, other 0/246, Norms 0/317, MLP 0/105, Attention 0/140

On the Hub · Downloads on Model Pulse