ZMIME

Aurora2-400M-A20M vs Hy4 flash Base

Compare documented capabilities and access. A dash means a comparable figure is unavailable.

Model specifications
SpecificationAurora2-400M-A20MAuroraAI ResearchHy4 flash BaseTencent
TaskBase language modelingMultimodal pretraining
Published capabilitiesEnglish base model pretrained on 100 billion tokens with one shared expert and 32 routed experts per layer.Pretrained checkpoint for continued training and adaptation. The Flash architecture uses a sparse Engram memory module.
Model size400M total / approximately 19M active parametersApproximately 220B total / 12B active per token
AccessPublic Transformers checkpoint for completion and adaptationDownloadable under the Tencent Hy License
SourcesModel weightsModel weights
InputsTextText, Images
WeightsOpen weights · Apache-2.0Open weights · Tencent Hy License
ReleasedNov 18, 2026Nov 18, 2026