Instructions to use HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4-Text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4-Text with Transformers:

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

pipe = pipeline("text-generation", model="HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4-Text")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4-Text")
model = AutoModelForCausalLM.from_pretrained("HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4-Text", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4-Text 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-R16E4-Text"
# 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-R16E4-Text",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4-Text

SGLang

How to use HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4-Text 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-R16E4-Text" \
    --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-R16E4-Text",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-R16E4-Text" \
        --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-R16E4-Text",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4-Text with Docker Model Runner:
```
docker model run hf.co/HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4-Text
```

WarpQuant-Qwen3.5-4B-R16E4-Text / README.md

HarimxChoi

docs: Qwen3.5 requirements

e329c3a verified 3 days ago

preview code

Raw

History Blame Contribute Delete

2.19 kB

	---
	library_name: transformers
	license: apache-2.0
	base_model: Qwen/Qwen3.5-4B
	pipeline_tag: text-generation
	tags:
	- qwen3.5
	- text-generation
	- quantization
	- post-training-quantization
	- warpquant
	- hadamard-transform
	- output-fisher
	- pytorch
	- llm
	language:
	- en
	- ko
	---

	# WarpQuant Qwen3.5-4B R16E4 Text

	Text-only export of the Qwen3.5-4B WarpQuant checkpoint. Projection weights use a signed-Hadamard block-GPTQ INT3 base, Output-Fisher selects the BF16 recovery columns, and the token embedding uses group-128 INT4.

	[Technical report](https://harimxchoi.github.io/projects/warpquant/) · [GitHub](https://github.com/HarimxChoi/WarpQuant) · [VLM model](https://huggingface.co/HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4)

	## Payload and evaluation

	The denominator is the 4,205,751,296-parameter text model; vision tensors are excluded.

	\| Format \| Text bpw \| Payload \| WikiText-2 PPL ↓ \| ARC-299 ↑ \| MMLU-13,943 ↑ \|
	\|---\|---:\|---:\|---:\|---:\|---:\|
	\| BF16 \| 16.00 \| 7.846 GiB \| 8.3885 \| 45.82 \| 39.58 \|
	\| Q4_K_M \| 5.13 \| 2.523 GiB \| 8.5472 \| 48.83 \| 39.48 \|
	\| IQ3_M \| 4.09 \| 2.015 GiB \| 10.6976 \| 42.81 \| 37.41 \|
	\| WarpQuant Fisher R16E4 \| 3.6514 \| 1.788 GiB \| 9.2494 \| 46.15 \| 38.13 \|

	The repository stores the quantized values in BF16-compatible safetensors. The reported payload is the packed-equivalent analytical size including codes, scales, recovery values, and column indices.

	## Usage

	Qwen3.5 currently requires the latest Transformers main branch:

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

	```python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model_id = "HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4-Text"
	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = AutoModelForCausalLM.from_pretrained(
	model_id,
	torch_dtype=torch.bfloat16,
	device_map="auto",
	)
	```

	## Citation

	```bibtex
	@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/}
	}
	```