LFM2.5-VL-3B-DSpark

Name: LFM2.5-VL-3B-DSpark
Author: Liquid Ai

Liquid Ai🇺🇸 United States

active

Compare with other models →

Version History

DSparkminorSeptember 24, 2026

Liquid AI released a 280M-parameter DSpark draft model for LFM2.5-VL-3B that enables speculative decoding, claiming decode speedups up to 3.13x on-device and 2.66x on H100 GPUs with no change to output quality. The drafter adds only 8.9% to the target model's parameter count and ships with day-one integrations for llama.cpp, MLX-VLM, and SGLang.

Coverage

analysisLiquid Ai

Liquid AI Releases DSpark Draft Model for LFM2.5-VL-3B, Claims Up to 3.13x Decode Speedup

Liquid AI has released LFM2.5-VL-3B-DSpark, a 280M-parameter speculative decoding drafter for its LFM2.5-VL-3B vision-language model. The company claims decode speedups up to 3.13x on Apple silicon and 2.66x on H100 GPUs, with day-one support for llama.cpp, MLX-VLM, and SGLang.

September 24, 2026 · 2:21 PM3 min read

Liquid AI LFM2.5-VL speculative decoding