llama-3.1-8b-instruct-npu-ov

llama-3.1-8b-instruct-npu-ov is an OpenVino int4 quantized version of Llama 3.1 Instruct, providing a very fast inference implementation, optimized for AI PCs using Intel NPU.

llama-3.1-instruct is a leading open source general foundation model from Meta.

Model Description

• Developed by: meta-llama
• Quantized by: llmware
• Model type: llama-3.1
• Parameters: 8 billion
• Model Parent: meta-llama/Meta-Llama-3.1-8B-Instruct
• Language(s) (NLP): English
• License: Llama 3.1 Community License
• Uses: General chat use cases
• RAG Benchmark Accuracy Score: NA
• Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website