DevQuasar/nvidia.Nemotron-Cascade-14B-Thinking-GGUF

Same weights, converted vs nvidia/Nemotron-Cascade-14B-Thinking. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Norms 0/161, Attention 0/160, MLP 0/120, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse