Image-Text-to-Text
MLX
Safetensors
English
Chinese
abliterated
qwen3.8
qwen3_5
uncensored
ai-red-team
red-teaming
apple-silicon
quantized
4-bit precision
8-bit precision
vision-language
multimodal
function-calling
reasoning
Instructions to use orcarouter/Qwen3.8-27B-Uncensored-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use orcarouter/Qwen3.8-27B-Uncensored-MLX with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("orcarouter/Qwen3.8-27B-Uncensored-MLX") config = load_config("orcarouter/Qwen3.8-27B-Uncensored-MLX") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Gated model You can list files but not access them
Preview of files found in this repository