Instructions to use techwithsergiu/Qwen3.5-0.8B-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use techwithsergiu/Qwen3.5-0.8B-bnb-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="techwithsergiu/Qwen3.5-0.8B-bnb-4bit")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("techwithsergiu/Qwen3.5-0.8B-bnb-4bit")
model = AutoModelForImageTextToText.from_pretrained("techwithsergiu/Qwen3.5-0.8B-bnb-4bit")
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

vLLM

How to use techwithsergiu/Qwen3.5-0.8B-bnb-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "techwithsergiu/Qwen3.5-0.8B-bnb-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "techwithsergiu/Qwen3.5-0.8B-bnb-4bit",
		"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/techwithsergiu/Qwen3.5-0.8B-bnb-4bit

SGLang

How to use techwithsergiu/Qwen3.5-0.8B-bnb-4bit 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 "techwithsergiu/Qwen3.5-0.8B-bnb-4bit" \
    --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": "techwithsergiu/Qwen3.5-0.8B-bnb-4bit",
		"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 "techwithsergiu/Qwen3.5-0.8B-bnb-4bit" \
        --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": "techwithsergiu/Qwen3.5-0.8B-bnb-4bit",
		"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 techwithsergiu/Qwen3.5-0.8B-bnb-4bit with Docker Model Runner:
```
docker model run hf.co/techwithsergiu/Qwen3.5-0.8B-bnb-4bit
```

Qwen3.5-0.8B-bnb-4bit

BNB NF4 4-bit quantization of Qwen/Qwen3.5-0.8B.

Retains the full visual tower — this is a VLM-capable model (image + text input). Primary use-case: Unsloth LoRA fine-tuning when you need image understanding in the fine-tuned result.

If you only need text fine-tuning, use techwithsergiu/Qwen3.5-text-0.8B-bnb-4bit instead — same backbone, visual tower removed, lighter VRAM footprint.

What was changed

Quantized with bitsandbytes NF4 double-quant (bnb_4bit_quant_type=nf4, bnb_4bit_compute_dtype=bfloat16)
Visual tower layers kept at bf16 (llm_int8_skip_modules) — required for correct image inference
lm_head.weight kept at bf16 for output quality

Model family

Model	Type	Base model
Qwen/Qwen3.5-0.8B	f16 · VLM · source	—
techwithsergiu/Qwen3.5-0.8B-bnb-4bit	BNB NF4 · VLM	Qwen/Qwen3.5-0.8B
techwithsergiu/Qwen3.5-text-0.8B	bf16 · text-only	Qwen/Qwen3.5-0.8B
techwithsergiu/Qwen3.5-text-0.8B-bnb-4bit	BNB NF4 · text-only	Qwen3.5-text-0.8B
techwithsergiu/Qwen3.5-text-0.8B-GGUF	GGUF quants	Qwen3.5-text-0.8B

The visual tower is a bf16 overhead that scales with model size (~0.19 GB for 0.8B, ~0.62 GB for 2B/4B, ~0.85 GB for 9B). BNB-quantized models are roughly 40% of the original f16 size (exact ratio varies by size).

Fine-tuning

Text-only LoRA fine-tuning — use the text-only BNB variant as training base: techwithsergiu/Qwen3.5-text-0.8B-bnb-4bit

Training pipeline (QLoRA · Unsloth · TRL): github.com/techwithsergiu/qwen-qlora-train

VLM (image + text) fine-tuning — refer to the official Unsloth guide: unsloth.ai/docs/models/qwen3.5/fine-tune

Pipeline diagram

Conversion

Converted using qwen35-toolkit — a Python toolkit for BNB quantization, visual tower removal, verification and HF Hub publishing of Qwen3.5 models.

Acknowledgements

Based on Qwen/Qwen3.5-0.8B by the Qwen Team. If you use this model in research, please cite the original:

@misc{qwen3.5,
    title  = {{Qwen3.5}: Towards Native Multimodal Agents},
    author = {{Qwen Team}},
    month  = {February},
    year   = {2026},
    url    = {https://qwen.ai/blog?id=qwen3.5}
}