# Liquid AI — LFM2.5-230M: Built to Run Anywhere

- Company: Liquid AI (liquid.ai)
- Announced: 2026-06-25
- Category: not stated
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.liquid.ai/blog/lfm2-5-230m
- Record: https://forck.live/items/16781-lfm2-5-230m-built-to-run-anywhere
- Subject: LFM / d1 models

Today, we're releasing LFM2.5-230M , our smallest model yet. It’s a fast, lightweight foundation for developers to fine-tune and deploy in agentic workflows. Built on the LFM2 architecture, it delivers exceptionally fast inference and runs everywhere, from cloud GPUs to low-cost CPUs (213 tok/s decode speed on Galaxy S25 Ultra, 42 tok/s on a Raspberry Pi 5). Despite its small size, it’s surprisingly capable at tool use and data extraction tasks. The base (LFM2.5-230M-Base) and post-trained (LFM2.5-230M) models are available today on Hugging Face . Check out our docs on how to run and fine-tune them locally. Training & Fine-tuning The model was pre-trained for 19T tokens, including a 32K context extension phase. We apply a lightweight post-training recipe designed to preserve flexibility for developers targeting their own downstream applications. The recipe consists of three stages: (1) supervised fine-tuning with distillation from LFM2.5-350M, (2) direct preference optimization, and (3) multi-domain reinforcement learning . …

---

Record: https://forck.live/items/16781-lfm2-5-230m-built-to-run-anywhere
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md