Skip to content
Log in

Qwen/Qwen3-VL-4B-Instruct

huggingface_int4_modelopt_tensorrt-edgellm
Qwen/Qwen3-VL-4B-Instruct architecture graph
Qwen/Qwen3-VL-4B-Instruct architecture graph
  • huggingface
  • AGX Thor
Labels
  • Image
  • Text
  • VLM
  • Generation
Build
Embedl-optimized
Precision
W4A16
Runtime
TensorRT Edge-LLM 0.10.1 with Embedl optimizations
Context length
4,096 tokens

Alibaba's 4B Qwen3-VL vision-language model for describing, reading and reasoning about images and video.

Files

Image Size

Model

docker.io/embedl/model-artifacts:qwen3-vl-4b.huggingface_int4_modelopt_tensorrt-edgellm.0d3371b1c6824482

 4.02 GiB

Runtime

docker.io/embedl/models:runtimes.tensorrt-edgellm.arm64.2026101815014ee0

 1.01 GiB