Hugging Face Blog·· 2026-08-21SelectedAI score66
Up to 3.2x Faster Inference with LFM2.5-DSpark
Up to 3.2x Faster Inference with LFM2.5-DSpark
AI introduction
LiquidAI released DSpark draft model checkpoints for the LFM2.5 series' LFM2.5-1.2B-Instruct, LFM2.5-2.6B, and LFM2.5-8B-A1B, speeding up inference via speculative decoding without changing output quality; throughput on H100 improves up to 3.18x, and up to 2.87x on edge devices.
Why it matters
The official release provides measured speedup data for the DSpark speculative decoding draft models along with llama.cpp and SGLang usage, so edge deployers can compare and judge the benefits.
Source images · Select to enlarge
Source: Hugging Face Blog · huggingface.co