engram-ae/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF

Same weights, converted vs nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 92 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/53, lm_head 0/1

On the Hub · Downloads on Model Pulse