Instructions to use AXERA-TECH/Qwen2.5-VL-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AXERA-TECH/Qwen2.5-VL-3B-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="AXERA-TECH/Qwen2.5-VL-3B-Instruct")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AXERA-TECH/Qwen2.5-VL-3B-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AXERA-TECH/Qwen2.5-VL-3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AXERA-TECH/Qwen2.5-VL-3B-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/Qwen2.5-VL-3B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AXERA-TECH/Qwen2.5-VL-3B-Instruct

SGLang

How to use AXERA-TECH/Qwen2.5-VL-3B-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/Qwen2.5-VL-3B-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/Qwen2.5-VL-3B-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/Qwen2.5-VL-3B-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/Qwen2.5-VL-3B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AXERA-TECH/Qwen2.5-VL-3B-Instruct with Docker Model Runner:
```
docker model run hf.co/AXERA-TECH/Qwen2.5-VL-3B-Instruct
```

Qwen2.5-VL-3B-Instruct

Commit History

Update README.md

d967363
verified

qqc1989 commited on Dec 16, 2025

优化tokenizer和 kv cache内存

0f72562

lihongjie commited on Dec 11, 2025

update axcl aarch64 bin

bb880b5
verified

wangli commited on Oct 20, 2025

支持多图和任意分辨率

891634b

lihongjie commited on Oct 17, 2025

update axcl aarch64 sh

df33ba5
verified

wangli commited on Oct 14, 2025

Update run_qwen2_5_vl_video_axcl_x86.sh

db4438f
verified

lihongjie007 commited on Sep 28, 2025

Update run_qwen2_5_vl_video_axcl_aarch64.sh

dcb588a
verified

lihongjie007 commited on Sep 28, 2025

Update README.md

9f1bf22
verified

wangli commited on Sep 15, 2025

Update README.md

aa91792
verified

wangli commited on Sep 15, 2025

Update README.md

0df3a06
verified

wangli commited on Sep 15, 2025

Delete qwen2_5-vl-3b-video-ax650

bc11ff9
verified

wangli commited on Sep 6, 2025

Delete qwen2_5-vl-3b-image-ax650

d34d57d
verified

wangli commited on Sep 6, 2025

Delete main

6083643
verified

wangli commited on Sep 6, 2025

Update README.md

a285fe2
verified

qqc1989 commited on Aug 23, 2025

ax650 支持chunk prefill模型

9cb8083

lihongjie commited on Aug 6, 2025

添加axcl二进制文件

f64e986

lihongjie commited on Jul 24, 2025

添加chunk prefill模型和axcl算力卡脚本

4ad77a2

lihongjie commited on Jul 24, 2025

Update README.md

08e93b8
verified

qqc1989 commited on Apr 22, 2025

Update README.md

33d32cb
verified

qqc1989 commited on Apr 6, 2025

Upload 8 files

b13ed9c
verified

qqc1989 commited on Apr 6, 2025

Upload ssd_horse.jpg

bfe8b62
verified

qqc1989 commited on Apr 6, 2025