Instructions to use AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary with Transformers:

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

pipe = pipeline("image-text-to-text", model="AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary

SGLang

How to use AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary 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 "AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary with Docker Model Runner:
```
docker model run hf.co/AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary
```

Qwen2.5-VL-7B-Instruct — Ternary Quantized

Ternary-quantized version of Qwen/Qwen2.5-VL-7B-Instruct, produced with ternary-quant.

Qwen2.5-VL is one of the most capable open-weight vision-language models. This ternary-quantized version targets lower memory use while preserving multimodal behavior in a HuggingFace-native, component-aware PTQ workflow.

Quantization details

Metric	Value
Scheme	tritplane3 (3-plane progressive ternary)
Components quantized	text_backbone, multimodal_connector (196 linear layers)
Vision encoder	Kept in FP16
Stored size	7341 MB (~7.2 GB)
FP16 size	13051 MB (~12.7 GB)
Compression ratio	1.8x

Usage

from ternary_quant.inference import load_ternary_model

model, processor = load_ternary_model(
    "AsadIsmail/Qwen2.5-VL-7B-Instruct-ternary",
    runtime_mode="metal"  # "cached" for NVIDIA/CPU
)

from PIL import Image
image = Image.open("photo.jpg")
inputs = processor(text="What is shown in this image?", images=image, return_tensors="pt")
inputs = {k: v.to(model.device) for k, v in inputs.items()}
outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0], skip_special_tokens=True))

Reproduce

pip install ternary-quant
ternary-quant quantize-broad Qwen/Qwen2.5-VL-7B-Instruct \
    --output ./Qwen2.5-VL-7B-Instruct-ternary \
    --components text_backbone multimodal_connector \
    --scheme tritplane3 --dtype float16 --eval