Back to home
vision model
2 articles tagged with this topic
DeepSeekvision model
Snap a Photo, Get Text in 3 Secs — DeepSeek Vision, Wired Up
DeepSeek's new vision model reads text from any photo—receipts, contracts, product shots. ¥0.1–0.3 per image, WeChat pay. I tested it on my ledger at
Aug 212 min read
Liquid AILFM2.5-VL-3B
Liquid AI packs 2GB vision model on phones — local AI finally tells what, where
Liquid AI ships LFM2.5-VL-3B: 2GB, 3.1B params, runs locally on iPhone 17. ScreenSpot-v2 score jumped 6 to 78.7 — local models now truly see.
Aug 122 min read