Model

LFM2.5-1.2B

A 1.2B-parameter small model introduced by Liquid AI, belonging to the LFM series and optimized for low-latency real-time inference.

Timeline (last 90 days)

Oct 22

Official data shows that on a single B200, LFM2.5-1.2B's p95 latency on RIPL is 14.4 to 28.4 times lower than Qwen3.5-0.8B's on vLLM.

Unverified50%

Official data shows that on a single B200, LFM2.5-1.2B's p95 latency on RIPL is 14.4 to 28.4 times lower than Qwen3.5-0.8B's on vLLM.