Skip to content
Log in

Qwen/Qwen3.5-0.8B

huggingface_fp16_tensorrt-edgellm
Qwen/Qwen3.5-0.8B architecture graph
Qwen/Qwen3.5-0.8B 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 0.8B Qwen3.5 model for chat, reasoning and long context, with images.

Files

Image Size

Model

docker.io/embedl/model-artifacts:qwen3-5-0-8b.huggingface_int4_embedl-flashhead-mtp_tensorrt-edgellm.8f86c75a8c4c6234

 1.98 GiB

Runtime

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

 1.01 GiB