Verified record · from the answer index

llama-3.1-8b-instruct-pb6

This container houses the Llama-3.1-8B-Instruct, which is an 8 billion parameter, instruction-tuned large language model created by Meta. NVIDIA NIM: runs as an API on your own GPUs.

model:ngc:nim/meta/llama-3.1-8b-instruct-pb6