IntellAgents/Nemotron-Labs-Diffusion-VLM-8B-GGUF

Same weights, converted (fewer layers) vs nvidia/Nemotron-Labs-Diffusion-VLM-8B. IntellAgents/Nemotron-Labs-Diffusion-VLM-8B-GGUF matches part of nvidia/Nemotron-Labs-Diffusion-VLM-8B (308 of its 531 tensors; the rest of nvidia/Nemotron-Labs-Diffusion-VLM-8B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/69, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse