Up to 3.2x Faster Inference with LFM2.5-DSpark
Liquid AI releases DSpark draft models for its LFM2.5 family, achieving up to 3.2x faster inference through speculative decoding without compromising output quality.
Hugging Face Blog · Aug 21, 2026
Liquid AI releases DSpark draft models for its LFM2.5 family, achieving up to 3.2x faster inference through speculative decoding without compromising output quality.