Instructions to use HarimxChoi/WarpQuant-Qwen3.8-27B-R16E4H4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HarimxChoi/WarpQuant-Qwen3.8-27B-R16E4H4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="HarimxChoi/WarpQuant-Qwen3.8-27B-R16E4H4")
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-Qwen3.8-27B-R16E4H4")
model = AutoModelForMultimodalLM.from_pretrained("HarimxChoi/WarpQuant-Qwen3.8-27B-R16E4H4", 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-Qwen3.8-27B-R16E4H4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HarimxChoi/WarpQuant-Qwen3.8-27B-R16E4H4"
# 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-Qwen3.8-27B-R16E4H4",
		"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-Qwen3.8-27B-R16E4H4

SGLang

How to use HarimxChoi/WarpQuant-Qwen3.8-27B-R16E4H4 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-Qwen3.8-27B-R16E4H4" \
    --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-Qwen3.8-27B-R16E4H4",
		"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-Qwen3.8-27B-R16E4H4" \
        --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-Qwen3.8-27B-R16E4H4",
		"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-Qwen3.8-27B-R16E4H4 with Docker Model Runner:
```
docker model run hf.co/HarimxChoi/WarpQuant-Qwen3.8-27B-R16E4H4
```

WarpQuant Qwen3.8-27B R16E4H4

This is the complete Qwen3.8-27B multimodal checkpoint produced with WarpQuant. It retains the vision tower and multimodal components while applying WarpQuant to the 64-layer text backbone.

Technical report · Code · Text-only model

Format

The text backbone uses signed Hadamard rotation, 3-bit group quantization, block-GPTQ reconstruction, and Output-Fisher weak-column recovery. Token embeddings and the language-model head use group-128 INT4.

Scope	Value
Text parameters	26,895,998,464
Text payload	3.616506953 bpw
Text payload size	11.323668 GiB
Projection group / tile	128 / 128
Vision tower	included
Multimodal projector	included

Text-backbone evaluation

Format	Text bpw	Payload	WT2 PPL ↓	ARC-299 ↑	MMLU-13,943 ↑	Commonsense ↑	GSM8K-500 flex ↑
BF16	16.00	50.11 GiB	6.9548	52.17	43.07	79.23	70.40
Q4_K_M	4.92	15.41 GiB	6.9656	50.84	42.90	79.23	75.20
IQ3_S	3.6940	11.57 GiB	7.1820	52.17	42.97	78.83	59.40
WarpQuant R16E4H4	3.6165	11.32 GiB	7.4737	56.86	42.72	78.83	61.00

GSM8K uses the same first 500 examples, 5-shot prompts, and flexible-extract accuracy for all four models.

KV cache and activation ablation

Configuration	PPL ↓	Top-1	KV compression @ 512
Weight-only	6.6468	reference	1.00×
K4/V4/R128	6.6495	97.65%	2.14×
Dynamic A8	6.7139	92.10%	1.00×
K4/V4/R128 + A8	6.6945	92.47%	2.14×

Use

from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "HarimxChoi/WarpQuant-Qwen3.8-27B-R16E4H4"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(model_id, 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://github.com/HarimxChoi/WarpQuant}
}