Instructions to use HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4")
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("HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4")
model = AutoModelForMultimodalLM.from_pretrained("HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4",
		"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/HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4

SGLang

How to use HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4 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 "HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4" \
    --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": "HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4",
		"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 "HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4" \
        --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": "HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4",
		"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 HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4 with Docker Model Runner:
```
docker model run hf.co/HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4
```

WarpQuant Qwen3.5-4B R16E4V4

Qwen3.5-4B quantized with signed Hadamard rotation, block-GPTQ, and Output-Fisher weak-column recovery. The projection layers use a 3.5-bpw INT3 base, selected columns are restored in BF16, and the token embedding and vision weights use group-128 INT4.

Technical report · GitHub · Text-only model

Format

Component	Format
Text projections	signed Hadamard + block-GPTQ INT3
Weak columns	Output-Fisher selected BF16 recovery
Token embedding	group-128 INT4
Vision weights	group-128 INT4
Full-model packed-equivalent rate	3.6912 bpw

The repository stores the quantized values in BF16-compatible safetensors for direct Transformers loading. The bpw value is the analytical packed payload including codes, scales, recovery values, and column indices.

Evaluation

Scope	Metric	Result
Text backbone	WikiText-2 PPL ↓	9.2494
Text backbone	ARC-Challenge, 299 ↑	46.15
Text backbone	MMLU, 13,943 ↑	38.13
Full VLM	ChartQA-128 exact ↑	44.53
Full VLM	ChartQA-128 relaxed ↑	53.91

Usage

Qwen3.5 currently requires the latest Transformers main branch:

pip install "transformers @ git+https://github.com/huggingface/transformers.git@main"

import torch
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

Citation

@misc{choi2026warpquant,
  author = {Harim Choi},
  title = {WarpQuant: Dual-Domain LLM Quantization via Hadamard Rotation and Output-Fisher Sensitivity},
  year = {2026},
  url = {https://harimxchoi.github.io/projects/warpquant/}
}