Unverified50% confidenceFactExact time
Hy4-Preview (HYV4) is a 780B-parameter Mixture-of-Experts (MoE) language model that activates only 49B parameters per token and has a context window of 1 million tokens.
1
Sources
50%
Confidence
Long-term
Relevance
10/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHBM4E is an enhanced version built on top of HBM4, targeting high-end AI training scenarios that are extremely sensitive to bandwidth.66% similarUnverifiedHymba是NVIDIA于2024年提出的混合头注意力架构，在同一层内同时部署SSM头和注意力头，通过可学习门控机制融合输出，在1.5B参数规模下超越同规模纯Transformer和纯SSM模型64% similarUnverifiedV4-Pro uses a Mixture of Experts (MoE) architecture with a total parameter count of 1.6 trillion (1.6T) and 49 billion (49B) active parameters.64% similarUnverifiedHY3 is a model launched by Tencent Hunyuan and is one of the strongest open-source models currently in the sub-300-billion-parameter category.63% similarUnverifiedHY3 adopts a Mixture of Experts (MoE) architecture with a total of 295 billion parameters, 21 billion activated parameters, 192 experts, and a Top-8 routing mechanism.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/972031API
curl https://kongchang.com/api/v1/knowledge/claims/972031MCP
get_claim(id=972031)