From the source
Liquid AI released an experimental DSpark draft model for its vision-language model LFM2.5-VL-3B, achieving decoding throughput improvements of up to 2.66× on GPUs and 3.13× on edge devices without changing output quality.
The drafter has approximately 280M parameters, increasing the deployed model’s parameter count by 8.9%.
It is available on Hugging Face with support in llama.cpp, SGLang, and MLX-VLM.
