IntellAgents/Nemotron-Labs-Diffusion-3B-GGUF

Same weights, converted vs nvidia/Nemotron-Labs-Diffusion-3B. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104

On the Hub · Downloads on Model Pulse