---
license: apache-2.0
base_model: prithivMLmods/Qwen3-VL-8B-Instruct-abliterated-v2
base_model_relation: quantized
library_name: mlx
pipeline_tag: image-text-to-text
language:
  - en
tags:
  - mlx
  - apple-silicon
  - qwen3_vl
  - vision
  - vision-language
  - image-text-to-text
  - abliterated
  - uncensored
  - 4-bit
---

# Qwen3-VL-8B-Instruct-abliterated-v2 — MLX 4-bit

This is an **MLX** (4-bit) conversion of
[`prithivMLmods/Qwen3-VL-8B-Instruct-abliterated-v2`](https://huggingface.co/prithivMLmods/Qwen3-VL-8B-Instruct-abliterated-v2), an abliterated (refusal-removed) build of Qwen3-VL-8B-Instruct.

It runs natively on **Apple Silicon** (M-series) via Apple's
[MLX](https://github.com/ml-explore/mlx) framework and
[`mlx-vlm`](https://github.com/Blaizzy/mlx-vlm) — typically faster than
llama.cpp/Metal for image encoding, with no separate vision-encoder (mmproj)
file needed.

> As of conversion, no MLX build of this model existed — this is a
> community conversion to bring it to Apple Silicon users.

## Use it in an app

This model is wired into the
[**Qwen3-VL Captioner**](https://github.com/GitDonkeyHubbed/qwen3vl-captioner)
desktop app — pick it from the MLX section of the model dropdown on a Mac and
it downloads + loads automatically.

## Use it directly (mlx-vlm)

```bash
pip install mlx-vlm
```

```python
from mlx_vlm import load, stream_generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

model, processor = load("LethalDonkey/Qwen3-VL-8B-Instruct-abliterated-v2-MLX-4bit")
config = load_config("LethalDonkey/Qwen3-VL-8B-Instruct-abliterated-v2-MLX-4bit")

messages = [
    {"role": "system", "content": "You are a helpful assistant that describes images accurately and in detail."},
    {"role": "user", "content": "Describe this image in detail."},
]
prompt = apply_chat_template(processor, config, messages, num_images=1)

for chunk in stream_generate(model, processor, prompt, image=["your_image.jpg"], max_tokens=512):
    print(chunk.text, end="", flush=True)
```

## Quantization

- **Bits:** 4
- **Format:** MLX (safetensors), converted with `mlx_vlm.convert`
- Choose **4-bit** for the smallest size / lowest memory, **8-bit** for the best
  quality, **6-bit** for a balance.

## Credits

- Base model: [prithivMLmods/Qwen3-VL-8B-Instruct-abliterated-v2](https://huggingface.co/prithivMLmods/Qwen3-VL-8B-Instruct-abliterated-v2) by **prithivMLmods**
- Original architecture: **Qwen3-VL** by Qwen / Alibaba
- MLX framework: **Apple** ([ml-explore/mlx](https://github.com/ml-explore/mlx))
- VLM tooling: **mlx-vlm** ([Blaizzy/mlx-vlm](https://github.com/Blaizzy/mlx-vlm))
- Converted for the [Qwen3-VL Captioner](https://github.com/GitDonkeyHubbed/qwen3vl-captioner) project

## License

Apache-2.0, inherited from the base model.