LethalDonkey/Gliese-Qwen3.5-9B-Abliterated-Caption-MLX-8bit

Gliese-Qwen3.5-9B-Abliterated-Caption — MLX 8-bit

This is an MLX (8-bit) conversion of `prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption`, a captioning-specialized, abliterated (refusal-removed) fine-tune of Qwen3-VL-8B-Instruct.

It runs natively on Apple Silicon (M-series) via Apple's MLX framework and `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** 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)

pip install mlx-vlm

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/Gliese-Qwen3.5-9B-Abliterated-Caption-MLX-8bit")
config = load_config("LethalDonkey/Gliese-Qwen3.5-9B-Abliterated-Caption-MLX-8bit")

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: 8
• —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/Gliese-Qwen3.5-9B-Abliterated-Caption by prithivMLmods
• —Original architecture: Qwen3-VL by Qwen / Alibaba
• —MLX framework: Apple (ml-explore/mlx)
• —VLM tooling: mlx-vlm (Blaizzy/mlx-vlm)
• —Converted for the Qwen3-VL Captioner project

License

Apache-2.0, inherited from the base model.