aiqbench analysis
Liquid AI's LFM2.5-VL-3B advances on-device vision-language capabilities by introducing native function calling and significantly improving object grounding for screen automation tasks. The model maintains competitive benchmark performance while fitting within a 3 GB memory footprint, enabling practical deployment across consumer electronics and industrial robotics without relying on cloud inference.
Liquid AI Releases LFM2.5-VL-3B: A 3B Vision-Language Model That Reads Screens, Grounds Objects, and Calls Tools On-Device
Liquid AI released LFM2.5-VL-3B, a 3.1B-parameter vision-language model built for on-device deployment. It averages 80.7 on ScreenSpot-v2 and lifts RefCOCO grounding from 57.1 to 87.9. Function calling is new to the VL line, with ToolSandbox moving from 26.4 to 59.5. The model fits in roughly 3 GB and decodes 228 tokens/s on an Apple M5 Max. The post Liquid AI Releases LFM2.5-VL-3B: A 3B Vision-Language Model That Reads Screens, Grounds Objects, and Calls Tools On-Device appeared first on MarkTechPost.
Yesterday, Liquid AI released LFM2.5-VL-3B. It is a 3.1B-parameter vision-language model built for on-device deployment. The model reads digital screens across mobile, web, and desktop. It grounds objects to coordinates, parses documents and charts, and calls tools from text or image input. Liquid AI reports an average of 69.4 across 28 vision benchmarks. That matches InternVL-3.5-4B and sits 0.7 points behind Qwen3.5-4B, both 4.7B models. The model is…
Excerpt shown under the publisher's RSS terms · 68 words · full text and figures are on the publisher's site
Related coverage
Accelerating vision-language models with LFM2.5-VL-DSpark
Hugging Face · Sep 24, 2026
[AINews] High Taste Testers Ep. 1
Latent Space · Oct 17, 2026
Liquid AI Releases LFM2.5-VL-3B-DSpark: Speculative Decoding for Vision-Language Models With Up to 3.13x Faster Decoding
MarkTechPost · Sep 25, 2026
[AINews] The Future of Latent Space
Latent Space · Sep 25, 2026