Hugging Face Blog·· 3 d ago
Run fast, private agents on-device with LFM2.5-24B-A2B
Run fast, private agents on-device with LFM2.5-24B-A2B
AI summary
LFM2.5-24B-A2B is a 24B-parameter reasoning model with just 2B active parameters, built for fast, private agents on-device. It thinks before it answers, calls tools, and works through multi-step tasks inside popular agent harnesses.
Selection record
Threshold 60Official, first-handFirst 71Second 71
AdmittedSum of both 142 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：发布AI推理模型及Agent评测
- Why it was chosen
- Liquid AI has released a 24B-parameter, 2B-active on-device reasoning model, with agentic benchmark comparisons against larger MoE models and a route to deployment.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Hugging Face Blog · huggingface.co