Tencent AI @TencentAI_News · 01 Sep 2026
1.5TB → 214GB. Seven times smaller, barely a dent. That's Hy4 preview. The trick is Sherry — our quantization method that packs weights down to 1.25 bits each. (The image shows how.) It also unlocks a new way to run it: stitch the GPUs you already have across machines, and https://t.co/b2b5iN7xZK
288 871Views
2 539Likes
302Reposts
84Replies
75Quotes
1 439Bookmarks
Is that a lot?
23.3×vs this author's median12 415 views is typical
62Percentile for this authorof 8 recent posts
99.8×vs 10K–100K median2 896 views is typical
13.8× audienceReachviews ÷ followers
1.04%Engagement rateof viewers reacted