DevQuasar/nvidia.Nemotron-Cascade-8B-Thinking-GGUF

Same weights, converted vs nvidia/Nemotron-Cascade-8B-Thinking. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: MLP 0/108, Norms 0/145, Attention 0/144, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse