Lfm2 5

Facts

Noted: LFM2.5-1.2B-Instruct, LFM2.5-2.6B, and LFM2.5-8B-A1B are models in the series · 2026-08-21
Noted: DSpark-applied models achieved more than a 2x speedup · 2026-08-21
Noted: LFM2.5-2.6B reached 2.67x on H100 and 2.27x on MacBook Pro with M4 Max · 2026-08-21
Noted: DSpark-applied LFM2.5 models show speculative decoding can push compact on-device models past a 2x speedup without trading accuracy · 2026-08-21

Connections

Produces of: liquid ai

Structured graph also available as JSON at /public/entities/lfm2-5. CC BY 4.0.

All coverage

1h ago

Liquid AI Applies DSpark to LFM2.5, More Than Doubling Speed on H100 and MacBook

Liquid AI applied the speculative decoding technology DSpark to three models in its compact LFM2.5 series: LFM2.5-1.2B-Instruct, LFM2.5-2.6B, and LFM2.5-8B-A1B. The DSpark-applied models achieved more than a 2x speedup while maintaining performance. LFM2.5-2.6B reached a 2.67x speedup on H100 and 2.27x on a MacBook Pro with M4 Max.