Liquid AI releases LFM2.5-24B-A2B, an agent model that runs on laptopsMachine translation
Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.
The open-weight model targets multi-step tool use, with base and post-trained weights available on Hugging Face. It has a 131,072-token context window. In Liquid AI’s tests, it scored 27.69 on AutomationBench but trailed a comparison model on SWE-Bench Verified, 51.00 to 66.20.
This source permits summary display only.
Read at the original source