Tencent open-sources Hunyuan Hy4-flash with 1M context
Tencent open-sourced Hunyuan Hy4-flash on Hugging Face and GitHub in FP8 and Base versions. The MoE multimodal model has 224B total parameters with 12B active, supports 1M-token context, and handles image-text-to-text tasks.
2026-11-17 ~ 2026-11-18 · 4 related posts
- Tencent releases Hunyuan Hy4-flash on Hugging Face: MoE multimodal image-text-to-text model — tencent · 2026-11-17
- Tencent quietly lists Hy4-flash model page on Hugging Face — coder543 · 2026-11-18
- Tencent open-weights Hunyuan Hy4 flash: 224B MoE with 12B active params and 1M context — TencentHunyuan · 2026-11-18
1 near-duplicate retellings: BreakfastFriendly728