---
base_model: Qwen/Qwen3-VL-2B-Instruct
library_name: mlx
pipeline_tag: image-text-to-text
tags:
  - mlx
  - qwen3-vl
  - vision-language-model
  - quantized
  - 4bit
license: apache-2.0
---

<p align="center">
  <a href="https://apps.apple.com/tr/app/vanta-local-ai-llm-chat/id6758898098">
    <img src="banner.png" alt="Vanta - Local AI LLM Chat" width="100%" />
  </a>
</p>

<h1 align="center">Qwen3-VL-2B-Instruct-4bit</h1>

<p align="center">
  A verbatim mirror of
  <a href="https://huggingface.co/mlx-community/Qwen3-VL-2B-Instruct-4bit">mlx-community/Qwen3-VL-2B-Instruct-4bit</a>,
  kept here so the <b>Vanta</b> iOS app always has a stable lower-RAM model to download from.
</p>

## Run it on your iPhone with Vanta

This is one of the built-in one-tap downloads in **Vanta - Local AI LLM Chat**, a
local-first AI chat app for iPhone and iPad. Vanta runs models like this one fully
on-device with Apple's MLX framework - no account and no cloud, your chats stay on
your device. Because it's a vision-capable model, you can also chat about images.

Vanta recommends this smaller model on RAM-tight devices where the 4B Thinking model
is likely too heavy.

**[Download Vanta on the App Store ->](https://apps.apple.com/tr/app/vanta-local-ai-llm-chat/id6758898098)**

---

> **This is a copy.** Every model file in this repository is an exact copy of
> [`mlx-community/Qwen3-VL-2B-Instruct-4bit`](https://huggingface.co/mlx-community/Qwen3-VL-2B-Instruct-4bit).
> We cloned it so that **Vanta Client always has a reliable, always-available source**
> to download this model from, independent of any upstream changes. All credit for the
> model weights and the MLX conversion goes to
> [mlx-community](https://huggingface.co/mlx-community), [Qwen](https://huggingface.co/Qwen),
> and the original authors.

---

## Model Details

- **Original Model:** [Qwen/Qwen3-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct)
- **Upstream MLX Repo:** [mlx-community/Qwen3-VL-2B-Instruct-4bit](https://huggingface.co/mlx-community/Qwen3-VL-2B-Instruct-4bit)
- **Quantization:** 4-bit
- **Format:** MLX SafeTensors
- **Framework:** [mlx-vlm](https://github.com/Blaizzy/mlx-vlm)
- **Model Type:** `qwen3_vl`
- **Task:** Image-text-to-text
- **Disk Size:** ~1.78 GB

## Conversion Details

The upstream model was converted to MLX format from
[`Qwen/Qwen3-VL-2B-Instruct`](https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct)
using `mlx-vlm` version **0.3.4**.

## Related Models

- **Default Vanta pick:** [TerminatorPower/Qwen3-VL-4B-Thinking-4bit](https://huggingface.co/TerminatorPower/Qwen3-VL-4B-Thinking-4bit)
- **Upstream MLX repo:** [mlx-community/Qwen3-VL-2B-Instruct-4bit](https://huggingface.co/mlx-community/Qwen3-VL-2B-Instruct-4bit)
- **Original:** [Qwen/Qwen3-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct)

## Usage

```python
from mlx_vlm import load, generate

model, processor = load("TerminatorPower/Qwen3-VL-2B-Instruct-4bit")

output = generate(
    model,
    processor,
    prompt="Describe this image.",
    image="path/to/image.jpg",
    max_tokens=512
)
print(output)
```

**CLI:**

```bash
python3 -m mlx_vlm.generate \
  --model TerminatorPower/Qwen3-VL-2B-Instruct-4bit \
  --image path/to/image.jpg \
  --prompt "Describe this image."
```

## License

This model inherits the [Apache 2.0 license](https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct)
from the original Qwen model. The mirror does not add any restrictions.