hoidhxd/NVIDIA-NemotronLabs-VoiceChat-11B-GGUF

Same weights, converted vs nvidia/NVIDIA-NemotronLabs-VoiceChat-11B. Same weights stored in another dtype (F32/I64 → F16/I64).

Tensors changed: other 0/297, Embeddings 0/21, Norms 0/557, lm_head 0/1, MLP 0/190, Attention 0/282

On the Hub · Downloads on Model Pulse