Liquid AI Releases On-Device Inference Model LFM2.5-24B-A2B
Understand the story
On October 14, 2026, Liquid AI released the reasoning model LFM2.5-24B-A2B via the official Hugging Face blog. The model uses a MoE (Mixture of Experts) architecture with 24B total parameters and only 2B activated per token, positioned for fast, private on-device agent scenarios. It is available on Hugging Face as open weights. This is the only report on the event so far; no further developments yet.
AI overview of reporting · Updated 5 days ago
Reporting timeline
Explore different aspects of the story through its reporting.
- Hugging Face BlogSelectedRun fast, private agents on-device with LFM2.5-24B-A2B
Liquid AI released LFM2.5-24B-A2B, a reasoning model with 24B total parameters and only 2B activated per token, aimed at fast private on-device agents, published with open weights on Hugging Face.
Story heat trend
Current heat3·Comparable peak10（10/14 02:00）·Comparable change over 24 hours -50%
The trend compares the same continuously observed sources, which may cover fewer sources than the current heat score. Hover or select the chart to inspect each hour; use the left and right arrow keys to navigate.