Instructions to use AXERA-TECH/Qwen3-VL-2B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AXERA-TECH/Qwen3-VL-2B-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="AXERA-TECH/Qwen3-VL-2B-Instruct")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AXERA-TECH/Qwen3-VL-2B-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AXERA-TECH/Qwen3-VL-2B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AXERA-TECH/Qwen3-VL-2B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AXERA-TECH/Qwen3-VL-2B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AXERA-TECH/Qwen3-VL-2B-Instruct

SGLang

How to use AXERA-TECH/Qwen3-VL-2B-Instruct 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 "AXERA-TECH/Qwen3-VL-2B-Instruct" \
    --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": "AXERA-TECH/Qwen3-VL-2B-Instruct",
		"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 "AXERA-TECH/Qwen3-VL-2B-Instruct" \
        --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": "AXERA-TECH/Qwen3-VL-2B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AXERA-TECH/Qwen3-VL-2B-Instruct with Docker Model Runner:
```
docker model run hf.co/AXERA-TECH/Qwen3-VL-2B-Instruct
```

Qwen3VL - ax 模型转换 - Language Model 转化报错问题咨询

by wangsh0111 - opened Nov 5, 2025

Discussion

wangsh0111

Nov 5, 2025

你好呀～非常感谢你们提供 Qwen3VL 的 ax 模型，然而，在我们的实际场景中，需要对 Qwen3VL 进行下游任务微调，我参考 https://github.com/AXERA-TECH/Qwen3-VL.AXERA/tree/main/model_convert 和 https://github.com/AXERA-TECH/Qwen2.5-VL-3B-Instruct.axera/tree/axcl/model_convert 进行模型转化。最终并未转化成功：Vision Encoder 可以成功转化； Language Model 转化的时候报错："AssertionError: model_type error qwen3_vl_text"。我注意到你们提供的 Qwen3VL demo 使用 Pulsar2-5.0，然而我使用的是 https://huggingface.co/AXERA-TECH/Pulsar2/tree/main 提供的工具链（目前最新版本4.2），请问我的报错是否是 Pulsar2 的版本原因，如果是，可否提供 Pulsar2-5.0 的镜像文件；如果不是，可否帮忙分析一下原因呢？

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment