LFM2-VL

Install

LFM2-VL needs the vlm extra, which pulls in transformers for the chat-template backbone.

pip install "libreyolo[vlm]"

Predict

LibreLFM2VL is a Python class, not a .pt checkpoint: it is not loaded through the LibreYOLO() factory, and the libreyolo CLI does not resolve it. The LibreVLM(...) factory (from libreyolo import LibreVLM) also reaches this family by alias, e.g. LibreVLM("lfm2-vl-450m"); the class used below is what it constructs. Weights come from Liquid AI's own Hugging Face repository, not a LibreYOLO mirror; the first call downloads and caches them locally, and logs a one-time license notice before it does.

from libreyolo import LibreLFM2VL, SAMPLE_IMAGE model = LibreLFM2VL(size="450m") # Open vocabulary: any words work, not a fixed class head. Sticky# across every later predict()/track() call until set again.model.set_classes(["person", "bicycle", "dog"])result = model(SAMPLE_IMAGE, save=True) for box in result.boxes:    print(box.cls, box.conf, box.xyxy)

from libreyolo import LibreLFM2VL, SAMPLE_IMAGE model = LibreLFM2VL(size="450m") # The escape hatch beneath the detection convenience: free-form# questions, counting, or any prompt the boxes wrapper doesn't cover.text = model.chat(SAMPLE_IMAGE, "Describe the scene in one sentence.")print(text)

result.boxes carries the parsed detections like any other family. Confidence is a placeholder: LFM2-VL emits no per-box score, so every detection gets the same constant confidence, and conf= only drops rows below that constant, it does not rank them. iou discards near-duplicate boxes of the same class above the given overlap, a side effect of greedy decoding repeating an object; it is not a class-wise NMS pass. Skip set_classes() and the vocabulary defaults to the COCO-80 names. See prediction for sources, streaming and result handling.

Variants

Two sizes: 450m and 1.6b, both from Liquid AI's LFM2.5-VL release, built for on-device deployment. LibreYOLO's benchmark harness has not measured this family, so there are no published accuracy numbers to compare them by; pick a size against your own compute budget.

LibreYOLO exposes this family for prediction only. train(), val() and export() all raise NotImplementedError: fine-tune upstream and load the result instead, dataset validation is skipped because a placeholder confidence would make COCO mAP misleading, and export is out of scope for a generative model with no state dict to trace.

Licensing

Citation

@article{liquidai2025lfm2,
 title={LFM2 Technical Report},
 author={Liquid AI},
 journal={arXiv preprint arXiv:2511.23404},
 year={2025}
}