ModelScope @ModelScope2022 · 01 Sep 2026
Hy4 preview just got a lot smaller! AngelSlim releases two GGUF builds for llama.cpp, compressing the 770B flagship to 435 GiB or 214 GiB. 🤖 https://t.co/28w6b0jyyG 📦 Q4_K_M at 435.20 GiB is the quality-first default. STQ1_0 cuts that to 213.66 GiB with mixed 1–2 bit
2 504Views
28Likes
5Reposts
3Replies
0Quotes
5Bookmarks
Is that a lot?
0.16×vs this author's median15 192 views is typical
20Percentile for this authorof 5 recent posts
0.91×vs 10K–100K median2 751 views is typical
17.58%Reachviews ÷ followers
1.44%Engagement rateof viewers reacted