---
library_name: mlc-llm
base_model: microsoft/Phi-3.5-vision-instruct
tags:
- mlc-llm
- web-llm
---

# Phi-3.5-vision-instruct-q4f16_1-MLC

This is the [Phi-3.5-vision-instruct](https://huggingface.co/microsoft/Phi-3.5-vision-instruct)
model in MLC format `q4f16_1`. The weights are identical to
[mlc-ai/Phi-3.5-vision-instruct-q4f16_1-MLC](https://huggingface.co/mlc-ai/Phi-3.5-vision-instruct-q4f16_1-MLC).
The accompanying web-llm library (`model_lib`) is compiled from a fork with
`num_crops` defaulted to `4` — matching Microsoft's
[`preprocessor_config.json`](https://huggingface.co/microsoft/Phi-3.5-vision-instruct/blob/main/preprocessor_config.json)
— rather than the `16` baked into mlc-ai's upstream build. This reduces
per-image compute ~3-5× and produces a stable 757 image-embed tokens for
typical photo aspects (matches the upstream HuggingFace token-count
formula `(h/336 * w/336 + 1)*144 + 1 + (h/336 + 1)*12`).

The model can be used for projects [MLC-LLM](https://github.com/mlc-ai/mlc-llm)
and [WebLLM](https://github.com/mlc-ai/web-llm).

## Example Usage

Install MLC LLM following the
[installation documentation](https://llm.mlc.ai/docs/install/mlc_llm.html#install-mlc-packages).

### Chat

```bash
mlc_llm chat HF://dixieclick/Phi-3.5-vision-instruct-q4f16_1-MLC
```

### REST Server

```bash
mlc_llm serve HF://dixieclick/Phi-3.5-vision-instruct-q4f16_1-MLC
```

### Python API

```python
from mlc_llm import MLCEngine

model = "HF://dixieclick/Phi-3.5-vision-instruct-q4f16_1-MLC"
engine = MLCEngine(model)

for response in engine.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": "https://www.ilankelman.org/stopsigns/australia.jpg",
                },
                {"type": "text", "text": "Describe this image please."},
            ],
        },
    ],
    model=model,
    stream=True,
):
    for choice in response.choices:
        print(choice.delta.content, end="", flush=True)
print("\n")

engine.terminate()
```

## Documentation

For more information on MLC LLM please visit the
[documentation](https://llm.mlc.ai/docs/) and
[GitHub repo](http://github.com/mlc-ai/mlc-llm).