Tencent Hy @TencentHunyuan · 28 Aug 2026
@TencentHunyuan's Hy4-preview runs in vLLM from day 0, verified on NVIDIA GPUs. 🎉 - 770B total, 49B active, 256 routed experts plus one shared - 1M context, but each query attends to just 2048 tokens - Only 21 of the 78 layers compute their own sparse index, the other 57 reuse
23 145Views
87Likes
5Reposts
7Replies
2Quotes
0Bookmarks
Is that a lot?
0.89×vs this author's median26 152 views is typical
38Percentile for this authorof 8 recent posts
7.99×vs 10K–100K median2 896 views is typical
44.81%Reachviews ÷ followers
0.44%Engagement rateof viewers reacted