Tencent AI @TencentAI_News · 29 Aug 2026
We compressed Hy4-preview from 1.5TB to ～200GiB GGUF and it still works well ! Meet MIX-STQ1_0.The trick isn’t just going low, it’s deciding where: calibration data picks each layer’s bit-width, some down to 1.31-bit STQ1_0, some up to 2.06-bit IQ2_XXS. Same budget, lower https://t.co/xK8d3BH5br
521 246Views
1 831Likes
196Reposts
85Replies
82Quotes
0Bookmarks
Is that a lot?
42.0×vs this author's median12 415 views is typical
75Percentile for this authorof 8 recent posts
180×vs 10K–100K median2 896 views is typical
24.9× audienceReachviews ÷ followers
0.42%Engagement rateof viewers reacted