Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start free brief

LiquidAI

Data verified

This page groups canonical LiquidAI model families and applies the same public scoring lane used by the main leaderboard.

Model count
9
Best model
40.7/100
LFM2.5-8B-A1B
Avg. top 3
24.4/100
Latest release
August 2026
Public-ranked
3
Supported
2

Provider models

ContextPricePublic score
LFM2.5-8B-A1BCurrent128K$0.00 / $0.003377.27s40.7Estimated
LFM2-24B-A2BEstablished32K$0.00 / $0.00920.42s17.96Supported
LFM2.5-1.2B-InstructCurrent32K$0.00 / $0.00N/AN/A14.64Supported
LFM2.5-2.6BCurrent128K$0.00 / $0.00N/AN/A
LFM2.5-230MCurrent32K$0.00 / $0.00N/AN/A
LFM2.5-350MCurrent32K$0.00 / $0.00N/AN/A
LFM2.5-Embedding-350MCurrent32K$0.00 / $0.00N/AN/A
LFM2.5-VL-1.6B-ExtractCurrent128KN/AN/AN/A
LFM2.5-VL-450MCurrent128K$0.00 / $0.00N/AN/A
Radar

LiquidAI release history

Full release history

Compare LiquidAI models