---
license: mit
language:
  - multilingual
tags:
  - nlp
  - code
  - audio
  - automatic-speech-recognition
  - speech-summarization
  - speech-translation
  - visual-question-answering
  - phi-4-multimodal
  - phi
  - phi-4-mini
---

## microsoft/Phi-4- multimodal -instruct-onnx

### Introduction

ONNX version of Phi4 multi modal to accelerate inference with ONNX Runtime.

This modal is quantized to int4 precision and runs on CUDA devices.

To run this model with ONNX Runtime:

Download the model:

```bash
git clone https://huggingface.co/microsoft/Phi-4-multimodal-instruct-onnx
```

Download the script to run the model:

```bash
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/refs/heads/main/examples/python/phi4-mm.py -o phi4-mm.py
```

Run the script

```bash
python phi4-mm.py -m Phi-4-multimodal-instruct-onnx/cuda/cuda-int4-rtn-blocksize-32 -e cuda
```

You will be prompted for images, audio files and a prompt.


The performance of the text component is similar the [phi4 mini ONNX models] (https://huggingface.co/microsoft/Phi-4-mini-instruct-onnx/blob/main/README.md)

### Model Description

- Developed by: Microsoft
- Model type: ONNX
- License: MIT
- Model Description: This is a conversion of Phi4 mini model for ONNX Runtime inference.

Disclaimer: Model is only an optimization of the base model, any risk associated with the model is the responsibility of the user of the model. Please verify and test for you scenarios. There may be a slight difference in output from the base model with the optimizations applied.

### Base Model

Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, generating text outputs, and comes with 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning, and direct preference optimization to support precise instruction adherence and safety measures.

See details [here](https://huggingface.co/microsoft/Phi-4-multimodal-instruct/blob/main/README.md)