Instructions to use MingZwhy/Qwen3-4B-W2.79-QAD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MingZwhy/Qwen3-4B-W2.79-QAD with Transformers:

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

pipe = pipeline("text-generation", model="MingZwhy/Qwen3-4B-W2.79-QAD")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MingZwhy/Qwen3-4B-W2.79-QAD")
model = AutoModelForCausalLM.from_pretrained("MingZwhy/Qwen3-4B-W2.79-QAD", 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 MingZwhy/Qwen3-4B-W2.79-QAD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MingZwhy/Qwen3-4B-W2.79-QAD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MingZwhy/Qwen3-4B-W2.79-QAD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MingZwhy/Qwen3-4B-W2.79-QAD

SGLang

How to use MingZwhy/Qwen3-4B-W2.79-QAD 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 "MingZwhy/Qwen3-4B-W2.79-QAD" \
    --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": "MingZwhy/Qwen3-4B-W2.79-QAD",
		"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 "MingZwhy/Qwen3-4B-W2.79-QAD" \
        --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": "MingZwhy/Qwen3-4B-W2.79-QAD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MingZwhy/Qwen3-4B-W2.79-QAD with Docker Model Runner:
```
docker model run hf.co/MingZwhy/Qwen3-4B-W2.79-QAD
```

Qwen3-4B — W2.79, QAD checkpoint

The quantization-aware-distillation checkpoint that on-policy distillation starts from, for the W2.79 arm. This is a starting point for training, not a finished model.

Code and recipe: MingZwhy/QAOPD.

This is a latent checkpoint — read before loading

The tensors here are bf16 and not quantized. Quantization-aware training keeps high-precision master weights and applies the quantizer inside the forward pass; what gets saved is the master copy. Loading this file directly gives you an unquantized model. It will not error, and it will score higher than the W2.79 model does.

Use it as STUDENT_MODEL for the OPD stage, which supplies the quantizer configuration itself:

BITWIDTH=w2.79 STUDENT_MODEL=<this checkpoint> bash scripts/opd/run_math.sh

For a model you can load and evaluate, use the recovered checkpoint MingZwhy/Qwen3-4B-W2.79-QAOPD instead.

Quantization


weights	mixed INT1.58 / INT4 in blocks of 256, 50% of blocks at INT4 → 2.79 bits effective
embedding, output head	INT4
activations	INT8
KV cache	16-bit during OPD and evaluation