Liquid AI has introduced LFM2.5-24B-A2B, a new local model aimed at improving on-device Agent reasoning and tool use. The model keeps the same 24 billion total parameters as its predecessor while activating only about 2 billion parameters per run. Compared with LFM2-24B-A2B, the new release expands pretraining data from 17 trillion to 33 trillion tokens and increases context length from 32K to 131K. Liquid AI said the model is trained to reason before answering and was reinforced directly inside Agent frameworks including OpenClaw, Hermes Agent, Pi, and OpenCode to practice multi-step tool calling and result handling. In the company’s demo, Hermes Agent ran on a MacBook without using a cloud model API, searched trending Hugging Face projects, compiled a briefing, and continued after follow-up prompts. Liquid AI’s tests said the model generated 184 tokens per second on Apple’s M5 Max, with peak speed reaching 1.7x that of comparable MoE models. On Agent benchmarks, it scored 48.09 on LiveClaw versus 38.19 for Qwen3.6-35B-A3B, and 27.69 on AutomationBench, more than three times Qwen’s result. On SWE-bench Verified, however, it scored 51%, below Qwen’s 66.2%.
Liquid AI has released LFM2.5-24B-A2B, a local model built to improve reasoning and tool use for on-device Agents.
The previous LFM2-24B-A2B focused mainly on runtime efficiency. The new version keeps the same 24 billion total parameters while activating only about 2 billion parameters at a time. It also expands pretraining data from 17 trillion to 33 trillion tokens and increases context length from 32K to 131K.
According to the company, the model is designed to reason before answering. It was also reinforced directly inside Agent frameworks including OpenClaw, Hermes Agent, Pi, and OpenCode, where it practiced chaining tool calls, handling returned results, and completing multi-step tasks.
In an official demo, Hermes Agent ran on a MacBook without calling a cloud model API. It searched trending projects on Hugging Face, compiled a briefing, and kept working after follow-up prompts.
Liquid AI said the model generated 184 tokens per second on Apple’s M5 Max, with top speed reaching 1.7 times that of comparable mixture-of-experts, or MoE, models.
On Agent benchmarks, LFM2.5-24B-A2B scored 48.09 on LiveClaw, above the 38.19 posted by Qwen3.6-35B-A3B. It scored 27.69 on AutomationBench, more than three times Qwen’s result. On the SWE-bench Verified coding benchmark, however, it reached 51%, below Qwen’s 66.2%.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
