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

File size: 1,379 Bytes

2c6d2d6

{
  "source": "/workspace/warpquant-qwen-fisher-20260815/source-bf16",
  "base": "/workspace/warpquant-qwen-fisher-20260815/base-3.50",
  "selection": "/workspace/warpquant-qwen-fisher-20260815/results/s1-empirical-selection.json",
  "selection_sha256": "402289f66ed4aeab46b64a95d2f89a934274848894276f289f1a2ca441232b73",
  "result_index": 1,
  "domain": "original",
  "base_selected_bpw": 3.5,
  "selected_values": 3565158400,
  "selected_average_bpw": 3.5499975047392005,
  "recovery_bits": 16,
  "group_size": 128,
  "recovery_scales": 0,
  "index_bits": 122176,
  "tensor_count": 182,
  "column_count": 3818,
  "corrected_values": 11132928,
  "auxiliary_bits": null,
  "embedding_bits": 4,
  "embedding_values": 635699200,
  "embedding_scales": 4966400,
  "visual_bits": 4,
  "visual_values": 331612160,
  "visual_scales": 2590720,
  "output_head_bits": null,
  "output_head_values": 0,
  "output_head_scales": 0,
  "remaining_bf16_values": 6795776,
  "total_values": 4539265536,
  "analytical_source_bpw": 3.691168773255921,
  "shard_sha256": {
    "model-00001-of-00003.safetensors": "a89c8d496b83982d94b03c2ecf9c5126c7abefd7abb4434ccf39141941c55bcd",
    "model-00002-of-00003.safetensors": "c3c6775dd8f0d3ba4a6ab66d9bef5f7bf44543190bb199e565f24768fe8f764c",
    "model-00003-of-00003.safetensors": "29be7fa61d03865564bc0da99fb8e1d3657e88253824c649605811e5b5ace4f7"
  }
}