intel-neural-chat-7b-v3-2-ov

intel-neural-chat-7b-v3-2-ov is an OpenVino int4 quantized version of Intel Neural Chat 7b, providing a fast, small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

intel-neural-chat-7b-v3-2 is a leading chat finetuned version of mistral 7b.

Model Description

• Developed by: intel
• Quantized by: llmware
• Model type: mistral-7b
• Parameters: 7 billion
• Model Parent: Intel/Neural-Chat-7B-V3-2
• Language(s) (NLP): English
• License: Apache 2.0
• Uses: General purpose chat
• RAG Benchmark Accuracy Score: NA
• Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website