LFM2.5-Encoders for Fast Long-Context Inference on CPU

Back to Articles

Why we built a general-purpose encoder How the encoders are built Benchmark Results Inference speed on CPU and GPU LFM2.5-Encoder demos How to use and fine-tune LFM2.5-Encoders Load and run the model Fine-tuning for your task Get started with LFM2.5-Encoders Citation Today, we release two new encoder models on Hugging Face: LFM2.5-Encoder-230M and LFM2.5-Encoder-350M. They match the quality of larger models but stay fast as inputs get longer. This means you can run document-scale jobs on the hardware you already have, even on CPU.

Here's what you get:

Strong for their size: match or beat larger encoders on GLUE, SuperGLUE, and multilingual tasks.

8,192-token context with latency that grows slowly as inputs get longer.