antirez @antirez · 02 Sep 2026
I'm optimizing tensor parallel execution across two MacBook M5 Max systems using RDMA. This is how fast DeepSeek v4 Flash Exp Vision can run in MXFP4 (full precision) right now *without* DSpark, so this is the min speed you get in practice. https://t.co/pTL0lTOxDy
18 196Views
289Likes
22Reposts
21Replies
2Quotes
48Bookmarks
Is that a lot?
1.05×vs this author's median17 262 views is typical
50Percentile for this authorof 4 recent posts
6.61×vs 10K–100K median2 751 views is typical
22.78%Reachviews ÷ followers
1.84%Engagement rateof viewers reacted