API Try Docs Blog

LFM3-VL-2B-ONNX

ONNX version of LFM3-VL-2B for cross-platform inference with ONNX Runtime.

Find architecture and usage details in the original model card.

Files

---

Each precision pairs a decoder with a vision encoder.

Precision	Decoder	Vision encoder	Size	Device
q4	decoder_q4	vision_encoder_q8	1.69 GB	CPU
q8	decoder_q8	vision_encoder_fp16	2.51 GB	CPU
q4f16	decoder_q4f16	vision_encoder_fp16	1.69 GB	GPU
q8f16	decoder_q8f16	vision_encoder_fp16	2.34 GB	GPU
fp16	decoder_fp16	vision_encoder_fp16	3.90 GB	GPU
fp32	decoder	vision_encoder	7.80 GB	Reference

Use with ONNX Runtime

---

The vision encoder maps each image, or each temporal patch of a video, to projected features. The decoder takes these features at the <|image|> and <|video|> placeholders of input_ids. For image and video preprocessing, use the values in processor_config.json.

Recommended sampling: temperature=0.1, top_p=1.0, top_k=50, min_p=0.0, repetition_penalty=1.1. More options in the ONNX guide.