# Liquid AI — LFM2.5-VL-3B: A Better and Faster Vision-Language Model for the Edge

- Company: Liquid AI (liquid.ai)
- Announced: 2026-08-12
- Category: not stated
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.liquid.ai/blog/lfm2-5-vl-3b
- Record: https://forck.live/items/16774-lfm2-5-vl-3b-a-better-and-faster-vision-language-model-for-the-edge
- Subject: LFM / d1 models

Today, we release LFM2.5-VL-3B , our most capable vision-language model. It delivers competitive vision performance against models twice its size, while running faster across a range of CPU and GPU deployments even compared with models that have fewer parameters. LFM2.5-VL-3B builds on our previous LFM2-VL-3B , with significant improvements in screen understanding, grounding, function calling, and multi-image input. LFM2.5-VL-3B is a non-reasoning model that answers directly, keeping latency low for real-time and on-device applications. The model is available today on Hugging Face and our Playground . Check out our docs on how to run and fine-tune it locally. What’s New LFM2.5-VL-3B extends the vision-language capabilities of our previous release with four major improvements: Screen/UI understanding. LFM2.5-VL-3B has a strong understanding of digital screens across mobile, web, and desktop. It averages 80.7 on ScreenSpot-v2, far ahead of the much larger Gemma-4-E4B (51.2) and Qwen 3.5 4B (78.5) and close behind the larger InternVL-3.5-4B (84.1) Function calling. …

---

Record: https://forck.live/items/16774-lfm2-5-vl-3b-a-better-and-faster-vision-language-model-for-the-edge
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md