Instructions to use huihui-ai/Huihui-Qwen3.8-27B-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huihui-ai/Huihui-Qwen3.8-27B-abliterated with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="huihui-ai/Huihui-Qwen3.8-27B-abliterated")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("huihui-ai/Huihui-Qwen3.8-27B-abliterated")
model = AutoModelForMultimodalLM.from_pretrained("huihui-ai/Huihui-Qwen3.8-27B-abliterated", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huihui-ai/Huihui-Qwen3.8-27B-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huihui-ai/Huihui-Qwen3.8-27B-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huihui-ai/Huihui-Qwen3.8-27B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated

SGLang

How to use huihui-ai/Huihui-Qwen3.8-27B-abliterated with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "huihui-ai/Huihui-Qwen3.8-27B-abliterated" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huihui-ai/Huihui-Qwen3.8-27B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "huihui-ai/Huihui-Qwen3.8-27B-abliterated" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huihui-ai/Huihui-Qwen3.8-27B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use huihui-ai/Huihui-Qwen3.8-27B-abliterated with Docker Model Runner:
```
docker model run hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated
```

Community MLX conversions with native MTP

by vsnake87 - opened 12 days ago

Discussion

vsnake87

12 days ago

Thanks to huihui-ai for creating and releasing the original model. These are independent community conversions of that work, maintained by KostkaIT.

I've prepared two independent MLX conversions of this model for local inference on Apple Silicon:

oQ6e
oQ4e

Both versions preserve the model's native MTP weights and are designed to work with oMLX without requiring a separate drafter model. I prefer this self-contained setup because it is simpler to use and maintain.

In my own testing, the oQ4e build retained almost all of the quality I was getting from Q8, while using less memory. Results will depend on the hardware, runtime, and settings, so feedback from other users is welcome.

These are independent community conversions maintained by KostkaIT. They are not official releases from Huihui or Qwen.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment