Phi-3-mini-4k-instruct — ONNX (INT4)

INT4-quantized ONNX export of Phi-3-mini-4k-instruct, a 3.8B-parameter lightweight language model from Microsoft. Optimized for CPU inference with int4 RTN block-32 quantization.

Mirrored for use with inference4j, an inference-only AI library for Java.

Original Source

• Repository: Microsoft
• License: mit

Usage with inference4j

try (TextGenerator gen = TextGenerator.builder().build()) {
    GenerationResult result = gen.generate("What is Java in one sentence?");
    System.out.println(result.text());
}

Model Details

Property	Value
Architecture	Phi-3 (3.8B parameters, 32 layers, 3072 hidden)
Task	Text generation / chat
Context length	4096 tokens
Quantization	INT4 RTN block-32 acc-level-4
Original framework	PyTorch (transformers)

License

This model is licensed under the MIT License. Original model by Microsoft.