Instructions to use yw223/Qwen3-8B-AWQ-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yw223/Qwen3-8B-AWQ-2bit with Transformers:

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

pipe = pipeline("text-generation", model="yw223/Qwen3-8B-AWQ-2bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yw223/Qwen3-8B-AWQ-2bit")
model = AutoModelForCausalLM.from_pretrained("yw223/Qwen3-8B-AWQ-2bit")
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 yw223/Qwen3-8B-AWQ-2bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yw223/Qwen3-8B-AWQ-2bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yw223/Qwen3-8B-AWQ-2bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yw223/Qwen3-8B-AWQ-2bit

SGLang

How to use yw223/Qwen3-8B-AWQ-2bit 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 "yw223/Qwen3-8B-AWQ-2bit" \
    --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": "yw223/Qwen3-8B-AWQ-2bit",
		"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 "yw223/Qwen3-8B-AWQ-2bit" \
        --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": "yw223/Qwen3-8B-AWQ-2bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yw223/Qwen3-8B-AWQ-2bit with Docker Model Runner:
```
docker model run hf.co/yw223/Qwen3-8B-AWQ-2bit
```

Qwen3-8B AWQ 2-bit

This repository contains an AWQ-style weight-only quantized derivative of Qwen/Qwen3-8B.

Quantization

Method: AWQ
Weight bits: 2
Activation precision: 16-bit
Scheme: W2A16 asymmetric group quantization
Group size: 128
Calibration dataset: c4
Backend path: Hugging Face transformers + llm-compressor
Experimental low-bit AWQ: yes

Validation

Validation has not been run yet.

License and Use

This model is derived from Qwen/Qwen3-8B and is released under the Apache 2.0 license. Use and redistribution must comply with the upstream model license and Hugging Face model terms.

Run Metadata

{
  "activation_dtype": "float16_or_bfloat16",
  "base_model": "Qwen/Qwen3-8B",
  "bits": 2,
  "config": "/nas/longleaf/home/yuanwu/Bias_Compressed_LLM/Quantization/AWQ/configs/qwen3_8b.yaml",
  "created_at": "2026-06-22T08:00:12.160687+00:00",
  "elapsed_seconds": 831.79,
  "environment": {
    "cuda_available": true,
    "cuda_devices": [
      {
        "capability": "8.9",
        "index": 0,
        "name": "NVIDIA L40S",
        "total_memory_gb": 44.39
      }
    ],
    "platform": "Linux-5.14.0-611.16.1.el9_7.x86_64-x86_64-with-glibc2.34",
    "python": "3.10.20",
    "torch": "2.11.0+cu130",
    "torch_cuda": "13.0"
  },
  "experimental_low_bit_awq": true,
  "method": "AWQ",
  "output_dir": "/users/y/u/yuanwu/Bias_Compressed_LLM/awq_outputs/Qwen3-8B-AWQ-2bit",
  "scheme": "W2A16"
}

Downloads last month: 27

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for yw223/Qwen3-8B-AWQ-2bit

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Quantized

(342)

this model