Qwen3.5-122B-A10B
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.
Input
Output
Context
262K
Max Output
66K
Parameters
122B
Technical Specifications
Model TypeVision
Context Window262K
Max Output Tokens66K
Parameters122B
Training Cutoff—
Licenseapache-2.0
Capabilities
Input Modalities
textimagevideo
Output Modalities
text
Features
function_callingjson_modereasoningstreamingtext_generationvision
Resources & Links
Estimated GPU Requirements for Qwen3.5-122B-A10B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.