Instructions to use J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Local Apps Settings

How to use J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ",
		"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/J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ

SGLang

How to use J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ 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 "J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ" \
    --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": "J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ",
		"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 "J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ" \
        --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": "J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ",
		"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 J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ with Docker Model Runner:
```
docker model run hf.co/J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ
```

Qwen3.5-2B (W4A16 Quantized via AutoRound)

This repository contains a W4A16 (4-bit weights, 16-bit activations) quantized version of Qwen/Qwen3.5-0.8B generated using Intel's AutoRound algorithm.

⚡ Quantization Details

The model was calibrated and quantized using production-grade settings to minimize accuracy degradation while significantly lowering VRAM requirements:

Quantization Algorithm: AutoRound
Bits / Precision: W4A16 (4-bit integer weights, 16-bit activation)
Group Size: 16 (provides higher reconstruction fidelity than standard 128)
Symmetric (sym): True
Calibration Samples (nsamples): 512
Sequence length (seqlen): 4096
Tuning Iterations (iters): 1000
Vision Tower (quant_nontext_module): False (Kept in BF16 to preserve visual reasoning and OCR precision)
Special Modules (layer_config): Multi-Token Prediction (mtp, mtp.fc) layers preserved in native bfloat16.

🚀 Usage & Quickstart

1. Inference via vLLM

For high-throughput production serving:

vllm serve J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound-GPTQ \
    --quantization auto-round \
    --dtype bfloat16 \
    --max-model-len 4096 \
    --gpu-memory-utilization 0.90

(Note: For the GPTQ format repo, you can set --quantization gptq if required by your backend).

📊 VRAM & Performance Benefits

Original Model (BF16): ~54 GB VRAM required (needs 2x A100/A6000 or 80GB VRAM)
Quantized Model (W4A16 Group 64): ~16–18 GB VRAM (can easily run on a single RTX 3090 / 4090 / A5000 24GB)
Speedup: Reduced memory bandwidth bottleneck leading to faster decoding token speeds.