TLDRocket
Sign in

Liquid AI releases LFM2.5-VL-3B, an on-device vision-language model for screen understanding, object grounding, and tool/function calling

Model release Provisional 86% confidence first seen

Liquid AI announced the release of LFM2.5-VL-3B, a 3B-class vision-language model designed to run on users’ own hardware. The model is positioned for on-device screen understanding, object grounding, multi-image inputs, and tool/function calling, with availability across multiple runtime formats and an LFM Open License v1.0 for limited free commercial use.

LFM2.5-VL-3B Liquid AI Apple M5 Max LFM Open License v1.0 M5 Max MarkTechPost RefCOCO ScreenSpot-v2 ToolSandbox

Source coverage

LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge Hugging Face official Liquid AI Releases LFM2.5-VL-3B: A 3B Vision-Language Model That Reads Screens, Grounds Objects, and Calls Tools On-Device MarkTechPost

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.