Qwen3.5-397B-A17B
Open SourceMultimodal
About
Alibaba's largest Qwen 3.5 model, featuring a Mixture-of-Experts architecture with 397B total parameters and 17B active per token (using 512 total experts with 10 routed + 1 shared active). Supports 201 languages with a native 262K token context window extensible to 1M tokens via YaRN. Includes a thinking/reasoning mode, tool calling with MCP integration, and unified vision-language capabilities through early fusion training.
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
Benchmark Scores(1)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 89.3 | diamond | Artificial Analysis |
