# LiquidAI

- Page: https://shared.btbytes.com/p/liquidai
- Date: 2026-03-05

> LFM2.5-230M: our smallest model yet, built to run fast anywhere (CPUs, NPUs, and GPUs) to enable agentic tasks on phones, robots, home and network automation devices. [X/liquidai](https://x.com/liquidai/status/2070148140368318884); Jun 26, 2026.


--

[Set Up LiquidAI LFM2.5-8B-A1B](https://x.com/noctus91/status/2064761762231271745)  + [Hermes Agent](https://shared.btbytes.com/p/hermes-agent)  locally in 10 minutes via `X/noctus91`. ^db45f5

--

[Liquid Demo \| Tool-Calling Agents on Consumer Hardware with LFM2-24B-A2B - YouTube](https://www.youtube.com/watch?v=WnxxW2jTDgE)

"LocalCoWork"

[No Cloud, No Waiting: Tool-Calling Agents on Consumer Hardware with LFM2-24B-A2B \| Liquid AI](https://www.liquid.ai/blog/no-cloud-tool-calling-agents-consumer-hardware-lfm2-24b-a2b); Mar 2026.

--

[maximecb/bebelm: CPU-only, pure-Rust implementation of LiquidAI's LFM2.5-8B-A1B · GitHub](https://github.com/maximecb/bebelm); Jun 2026.

> This model is very capable and has only 1B active parameters, making it possible for the model to run at interactive speeds without a GPU.

> This package intentionally has very few dependencies and requires no extra system packages to run, making it easy to build and run. This is a library crate which can be imported into your Rust projects