LFM2.5-Encoders for Fast Long-Context Inference on CPU
Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.
LFM2.5-Encoders achieve 3-10x smaller model sizes than comparable models while maintaining quality, enabling CPU-based inference for document-scale NLP tasks like intent routing and text classification at significantly lower costs. They scale better with input length, maintaining throughput as inputs grow, unlike alternatives that sharply decrease in performance. This enables running NLP workloads like PII detection and policy linting cheaply and continuously on existing hardware.
LFM2.5-Encoder ships in 230M and 350M variants with 8,192-token context, and the 230M model is reported fastest on CPU at every tested sequence length while outperforming ModernBERT-base on benchmark quality. For production teams, this makes long-document classifiers, routers, PII detectors, and policy filters more viable on existing CPU fleets instead of requiring GPU capacity or aggressive chunking.