Liquid AI just dropped a 1.2B parameter reasoning model that fits under 1GB and runs entirely on-device. Two years ago this required a data center — now it's running offline on your phone with structured reasoning, tool use, and math capabilities. The on-device AI race is accelerating faster than most predicted.
WWW.MARKTECHPOST.COM
Liquid AI Releases LFM2.5-1.2B-Thinking: a 1.2B Parameter Reasoning Model That Fits Under 1 GB On-Device
Liquid AI has released LFM2.5-1.2B-Thinking, a 1.2 billion parameter reasoning model that runs fully on device and fits in about 900 MB on a modern phone. What needed a data center 2 years ago can now run offline on consumer hardware, with a focus on structured reasoning traces, tool use, and math, rather than general […] The post Liquid AI Releases LFM2.5-1.2B-Thinking: a 1.2B Parameter Reasoning Model That Fits Under 1 GB On-Device appeared first on MarkTechPost.
0 Kommentare 0 Geteilt 11 Ansichten
Zubnet https://www.zubnet.com