ZMIME

DaisyRose-27B vs Hy4 flash Base

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

Model specifications
SpecificationDaisyRose-27BRadixArkHy4 flash BaseTencent
TaskAgentic codingMultimodal pretraining
Published capabilitiesPost-trained from Qwen3.8-27B on 1,200 agent tasks. RadixArk reports 12% pass@1 on Terminal-Bench 4.1.Pretrained checkpoint for continued training and adaptation. The Flash architecture uses a sparse Engram memory module.
Model size27B parametersApproximately 220B total / 12B active per token
AccessPublic BF16, FP8 and NVFP4 checkpointsDownloadable under the Tencent Hy License
SourcesPublisher documentationModel weights
InputsText, ImagesText, Images
Context window262,144 tokens—
WeightsOpen weights · Apache-2.0Open weights · Tencent Hy License
ReleasedNov 18, 2026Nov 18, 2026