About Qwen3 VL 2B - Instruct
Qwen/Qwen3-VL-2B-Instruct is a multimodal LLM that excels at lightweight vision‑language tasks such as visual question answering, document and UI understanding, and general image‑grounded chat, while being small enough for edge or resource‑constrained environments.
Some other noteworthy use cases of Qwen/Qwen3-VL-2B-Instruct include OCR and document analysis across many languages, and agentic interactions that involve interpreting screen content or layouts before deciding on actions.
| Metric | Value |
|---|---|
| Parameter Count | 2 billion |
| Mixture of Experts | No |
| Context Length | 256,000 tokens |
| Multilingual | Yes |
| Quantized* | No |
*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.
Ready to build with Qwen3 VL 2B - Instruct?
Try Qwen3 VL 2B - Instruct in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "qwen3-vl-2b-instruct",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'API endpoint
See the API reference for request and response formats.
https://hub.oxen.ai/api/ai/chat/completions