meshllm/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_XL-MTPv2-GGUF
Quantization vs nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16. meshllm/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_XL-MTPv2-GGUF is a GGUF quantization (Q5_1/Q4_K) of the same weights: 89 tensors match exactly and 2 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/89, lm_head 0/1
1 derivatives checked
- meshllm/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_XL-MTPv2-layers: Same weights, repacked (fewer layers)