ERNIE 4.5 21B A3B
A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heterogeneous MoE structures and modality-isolated routing. Supporting an extensive 131K token context length, the model achieves efficient inference via multi-expert parallel collaboration and quantization, while advanced post-training techniques including SFT, DPO, and UPO ensure optimized performance across diverse applications with specialized routing and balancing losses for superior task handling.
Input
Output
Context
120K
Max Output
8K
Parameters
21B
Technical Specifications
Capabilities
Input Modalities
Output Modalities
Features
Estimated GPU Requirements for ERNIE 4.5 21B A3B
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.