Liquid AI Launches LFM2.5-VL-3B: A Lightweight On-Device Vision-Language Model
JosephJacks_ · x · 2026-08-13
Liquid AI has released LFM2.5-VL-3B, a lightweight vision-language model built for mobile, web, and desktop environments. It is capable of reading screens, documents, and the physical world.
Built on the LFM2.5-2.6B base with a SigLIP2 400M vision encoder and pre-trained on 34T tokens, it achieves comparable or better scores than models up to 2.6x its size. It scores 80.7 on ScreenSpot-v2 and 73.1 on RealWorldQA, while supporting tool calling from both text and image inputs.
Related event: LiquidAI Releases LFM2.5-VL-3B Edge Multimodal Model(7 posts)→
More from Models
- Grok 4.6 Released: Better Performance at Half the Price of Rivals — NinaDSchick · 2026-08-13
- DeepSeek V4 Pro Offers 10x Cheaper Cost Per Task Than GLM5.2 — ojasvi_yadav · 2026-08-13
- DeepSeek API Requests Timeout Amid Suspected Technical Issues — cedric_chee · 2026-08-13
- Free ChatGPT Users Silently Throttled for Overusing the 'Think' Button — Sauers_ · 2026-08-13
- Elon Musk Pushes Grok: Major Leap in Real-World Task Performance — elonmusk · 2026-08-13
- Hands-On Comparison: Grok 4.6 Edges Out DeepSeek in Success Rate, but Lags on Price — vista8 · 2026-08-13