Tencent has released Hy4 Flash, a 220 billion parameter multimodal mixture-of-experts model, available on Hugging Face. The model features a 1 million token context window and utilizes a sparse expert architecture with 12 billion active parameters per token. Its license includes a revenue trigger, requiring a separate agreement for API offerings exceeding $50 million in annual revenue. AI
IMPACT This release offers a large-scale MoE model with a significant context window, potentially impacting research and development in efficient LLM architectures.
RANK_REASON Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=1 ai=1.0]
- AngelSlim
- AngelSlim/Hy4-flash-GGUF
- bfloat16
- engram
- Fp8
- Hugging Face
- Hy4 Flash
- LatentMoE
- Q4_K_M GGUF
- Tencent
- Tencent Hy License
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →