# Liquid AI — LFM2.5-24B-A2B: Built for Fast On-Device Agents

- Company: Liquid AI (liquid.ai)
- Announced: 2026-10-13
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://www.liquid.ai/blog/lfm2-5-24b-a2b
- Record: https://forck.live/items/20538-lfm2-5-24b-a2b-built-for-fast-on-device-agents
- Subject: LFM / d1 models
- Open weights: yes
- Models affected: LFM2.5-24B-A2B, LFM2.5-24B-A2B-Base, LFM2.5-230M
- Context window: 131,072 tokens

Liquid AI released LFM2.5-24B-A2B, a 24B-parameter reasoning model with 2B active parameters, designed for fast, private on-device agents. The model is competitive with larger MoEs on agentic and tool-use benchmarks, scoring 48.09 on LiveClaw versus 38.19 and 27.69 on AutomationBench versus 8.72. It runs up to 1.7× faster than comparable MoEs on-device, achieving 184 tokens/s on an Apple M5 Max and over 21K output tokens/s on a single NVIDIA B300 GPU.

## Evidence

Verbatim from https://www.liquid.ai/blog/lfm2-5-24b-a2b:

> Today, we release LFM2.5-24B-A2B , a 24B-parameter reasoning model with just 2B active parameters, built for fast, private agents on-device.

## Follow-ups

- Unite.AI (reported, 13 Oct): Liquid AI Releases Open-Weight LFM2.5-24B-A2B for On-Device Agents — https://forck.live/items/20576-liquid-ai-releases-open-weight-lfm2-5-24b-a2b-for-on-device-agents

---

Record: https://forck.live/items/20538-lfm2-5-24b-a2b-built-for-fast-on-device-agents
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md