majentik/Nemotron-3-Nano-4B-RotorQuant-GGUF-IQ4_XS
Quantization vs nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16. majentik/Nemotron-3-Nano-4B-RotorQuant-GGUF-IQ4_XS is a GGUF quantization (IQ4_XS) of the same weights: 43 tensors match exactly and 2 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/43, lm_head 0/1