Liquid AI has released two open-weight models that return yes/no, multiple-choice and scored answers in a single forward pass instead of generating tokens, with vendor-reported latency as low as 16 milliseconds on an NVIDIA Jetson edge board. The benchmarks are the company's own; independent verification is absent.
Google DeepMind released EmbeddingGemma 2, a 740-million-parameter open model under Apache 2.0 that maps text, images, video and audio into one shared embedding space, enabling private offline media search on consumer hardware.
Liquid AI's new 280M-parameter DSpark drafter guesses ahead so the LFM2.5-VL-3B vision model verifies instead of computing every token. All speedups are self-reported; here is how the technique works and where its gains stop.