Instructions to use lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4")
model = AutoModelForImageTextToText.from_pretrained("lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4",
		"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/lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4

SGLang

How to use lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4 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 "lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4" \
    --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": "lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4",
		"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 "lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4" \
        --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": "lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4",
		"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 lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4 with Docker Model Runner:
```
docker model run hf.co/lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4
```

Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4

This repository contains an NVFP4-compressed version of huihui-ai/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated.

The language model weights are compressed to NVFP4 for efficient inference on recent NVIDIA GPUs, while the multimodal weights are kept in BF16 and repacked into a separate model-multimodal-extra.safetensors file so that Qwen3_5ForConditionalGeneration behavior is preserved.

What Was Quantized

Source model: huihui-ai/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated
Quantization method: llmcompressor one-shot NVFP4
Calibration dataset: neuralmagic/calibration (LLM split)
Calibration samples: 512
Calibration sequence length: 2048
Quantized targets: Linear
Excluded from quantization:
- lm_head
- all model.visual.* linear layers
- linear_attn.in_proj_a
- linear_attn.in_proj_b

Repository Layout

model-00001-of-00005.safetensors to model-00005-of-00005.safetensors
- NVFP4 main language-model shards
model-multimodal-extra.safetensors
- BF16 multimodal tensors preserved from the source checkpoint
model.safetensors.index.json
- combined index for the main NVFP4 shards plus multimodal extra tensors
processor_config.json
- multimodal processor config copied from the source model
recipe.yaml
- the quantization recipe used for this build

Stored Tensor Metadata

total_parameters: 16713682960
total_size: 19743450720
hybrid_extra_tensor_count: 333
hybrid_extra_tensor_bytes: 921460192

Serving Notes

Tested locally with:

vllm/vllm-openai:cu130-nightly
vLLM 0.17.2rc1.dev153+g39474513f
NVIDIA RTX 5090
VLLM_NVFP4_GEMM_BACKEND=marlin

Observed behavior with reasoning enabled:

POST /v1/chat/completions
- returns message.reasoning
- can also return a normal message.content if max_tokens is large enough
POST /v1/responses
- returns reasoning blocks under output[].type = "reasoning"
- returns final text under output[].type = "message" and content[].type = "output_text"

For robust client integration, prefer reading the structured responses output instead of assuming the top-level text field is populated.

Example vLLM Command

vllm serve /path/to/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4 \
  --reasoning-parser qwen3 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder \
  --gpu-memory-utilization 0.95 \
  --kv-cache-dtype fp8

Notes

The source model's safety, licensing, and usage constraints still apply.
This repo keeps multimodal capability by preserving the original visual tower in BF16 instead of re-quantizing it.

Downloads last month: 14

Safetensors

Model size

17B params

Tensor type

BF16

F32

F8_E4M3

Model tree for lyf/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4

Base model

Qwen/Qwen3.5-27B

Finetuned

Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled

Finetuned

huihui-ai/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated

Quantized

(11)

this model

lyf
/

Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-NVFP4