LocalAI-io/dinov3-vitl16-pretrain-lvd1689m-GGUF

Same weights, converted vs facebook/dinov3-vitl16-pretrain-lvd1689m. Same weights stored in another dtype (F32 → F16/F32).

Tensors changed: Embeddings 0/2, Attention 0/168, other 0/48, MLP 0/96, Norms 0/98

On the Hub · Downloads on Model Pulse