mlx-community/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct-4bit
Quantization vs nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct. mlx-community/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct-4bit is a quantized version of the other (U32/F16).
Quantization vs nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct. mlx-community/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct-4bit is a quantized version of the other (U32/F16).