← Back to the wire

LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge

AchievementModelAug 12, 2026

LFM2.5-VL-3B pairs a SigLIP2 400M NaFlex vision encoder with the LFM2.5-2.6B text backbone, pre-trained on roughly 34T tokens. The model improves screen understanding, grounding, multi-image reasoning, and function calling over prior releases. It leads its size class on real-world image tasks and matches peers on tool use. Available on Hugging Face, it ships with support across llama.cpp, vLLM, and ONNX.

Receipt № 13381 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

LFM2.5-2.6BModelLFM2.5-VL-3BModelSigLIP2 400M NaFlexModel
Canonical: https://huggingface.co/blog/LiquidAI/lfm2-5-vl-3b