DevQuasar-13/nvidia.Llama-3_1-Nemotron-Ultra-253B-v1-GGUF

Quantization vs nvidia/Llama-3_1-Nemotron-Ultra-253B-v1. DevQuasar-13/nvidia.Llama-3_1-Nemotron-Ultra-253B-v1-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 146 tensors match exactly and 501 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/146, MLP 0/243, Attention 0/256, lm_head 0/1

On the Hub · Downloads on Model Pulse