9B parameter hybrid language model with Gated DeltaNet and dual thinking modes.
849
Qwen3.5-9B is a 9 billion parameter hybrid language model from the Qwen series by the Qwen Team at Alibaba Group. It uses a hybrid architecture combining Gated Delta Networks with sparse Mixture-of-Experts for high-throughput inference. The model supports seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient general-purpose dialogue). It supports over 200 languages and dialects.
| Vendor | AMD |
| License | Apache-2.0, MIT |
| Source | https://github.com/amd-enterprise-ai/aim-build |
| Revision | 9378816494e45a930c41928465bae7a14bf6d3b2 |
| Built | 2026-06-26T15:48:53Z |
Content type
Image
Digest
sha256:ee1201261…
Size
9.9 GB
Last updated
3 months ago
docker pull amdenterpriseai/aim-radeon-qwen-qwen3-5-9b:0.12.0-preview