Most decisions need a fast model, not a big one: Liquid AI open-sources d1-3B
JosephJacks_ · x · 2026-10-08
Liquid AI open-sourced d1-3B, a vision-language decision model, and d1-omni-600M, which takes text, images, and audio. The pitch: most decisions need a fast model, not a big one — targeting low-latency real-time decision scenarios rather than general chat.
Related event: Liquid AI Open-Sources d1 Decision Models: 3B and 600M Multimodal Family(7 posts)→
More from Multimodal
- Midjourney posts Office Hours recording from October 7 — midjourney · 2026-10-08
- Local 3B music model writes the track, Claude Code makes the MV in 15 minutes from one prompt — Pleasant_Salt6810 · 2026-10-08
- Runway brings its video generation directly into ChatGPT: brief, generate, and give notes in one chat — runwayml · 2026-10-08
- 280+ generations to make Superman vs Saitama: MiniMax H3 workflow lessons — Automatic-Building84 · 2026-10-08
- Gossip Goblin Held Up as Proof AI Art Can Rise Above the Slop, With a Movie Trailer — PossibleVariety7927 · 2026-10-08
- 128,000 Micro-Dramas Launched in Q1 2026, Over 95% AI-Generated, Epoch AI Reports — Jsevillamol · 2026-10-08