openchat-3.6-8b-20240522-ov

openchat-3.6-8b-202440522-ov is an OpenVino int4 quantized version of OpenChat-3.6-8b-20240522, providing a fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

openchat-3.6-8b-202440522 which is a popular leading chat finetuning of Llama 3.

Model Description

• Developed by: openchat
• Quantized by: llmware
• Model type: llama-3
• Parameters: 8 billion
• Model Parent: openchat/openchat-3.6-8b-20240522
• Language(s) (NLP): English
• License: Llama 3 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