julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF
Quantization vs nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16. julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF is a GGUF quantization (T100/Q8_0) of the same weights: 53 tensors match exactly and 1 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/53