phi-3-onnx

phi-3-onnx is an ONNX int4 quantized version of Microsoft Phi-3-mini-4k-instruct, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

Model Description

• Developed by: microsoft
• Quantized by: llmware
• Model type: phi3
• Parameters: 3.8 billion
• Model Parent: microsoft/Phi-3-mini-4k-instruct
• Language(s) (NLP): English
• License: Apache 2.0
• Uses: Chat, general-purpose LLM
• Quantization: int4

Model Card Contact

llmware on hf

llmware website