ZMIME

Hy4 flash Base vs Aion 1.0 Instruct 2.3B

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

Model specifications
SpecificationHy4 flash BaseTencentAion 1.0 Instruct 2.3BMicrosoft
TaskMultimodal pretrainingOn-device language generation
Published capabilitiesPretrained checkpoint for continued training and adaptation. The Flash architecture uses a sparse Engram memory module.Windows-oriented instruction model for local text generation, including document and email tasks.
Model sizeApproximately 220B total / 12B active per token2.3B parameters
AccessDownloadable under the Tencent Hy LicenseDownloadable checkpoint
Operating limits—32K-token context window
SourcesModel weightsModel weights
InputsText, ImagesText
WeightsOpen weights · Tencent Hy LicenseOpen weights · MIT
ReleasedNov 18, 2026Nov 18, 2026