Liquid AI's LFM2.5-24B-A2B: a local MoE model for agent tasks
Melvin Vivas · X post · 2026-10-14 · Open on X
Topics: LLM Fundamentals, AI Agents, Tool Use & MCP, Industry Trends & Job Market · Level: intermediate
Summary
Liquid AI released LFM2.5-24B-A2B, the largest model in the LFM2.5 family. It is an efficient local model for laptops and PCs that works through multi-step tasks inside agent harnesses. The creator plans to try it in a Colab notebook first, to see if it fits on a T4 GPU, and then with Coworker.
Key points
- It has 24B total parameters but only 2B active per token (mixture-of-experts style), which makes it efficient.
- The context window is expanded to 131K tokens.
- It is built to run locally on laptops and PCs for multi-step tasks inside popular agent harnesses.
- A practical first test: load it in a Google Colab notebook and check whether it fits on a free T4 GPU.
Resources mentioned
- LFM2.5-24B-A2B · tool · huggingface.co · free
Liquid AI's local model for multi-step agent tasks, with 24B total and 2B active parameters and a 131K-token context. - Liquid AI (@liquidai) on X · website · x.com · free
Liquid AI's family of efficient foundation models, used here as the example of a model you can run in the browser with ONNX.
Also in: Trying Liquid AI Decision Models (d1, d1 ultra) via API (Melvin Vivas on X · notes), Liquid RIPL: Low-Latency Inference Engine for LFMs (Melvin Vivas on X · notes), ONNX + Transformers.js: Run Models Like Liquid LFM in the Browser (Melvin Vivas on X · notes), Try Liquid AI's open d1-3B decision model in Colab (Melvin Vivas on X · notes) and 30 more - Google Colab · tool · colab.research.google.com · free · recommended by both Bashiri Smith & Melvin Vivas
Free GPU notebooks.
Also in: Run LightOnOCR-3 0.8B and Other Open Models on a Free Colab T4 (Melvin Vivas on X · notes), Try Liquid AI's open d1-3B decision model in Colab (Melvin Vivas on X · notes), Google Colab notebooks for new open models, built by a coding agent (Melvin Vivas on X · notes), A100 80GB GPUs in Google Colab via Google AI Pro plans (Melvin Vivas on X · notes) and 27 more - Coworker (donvito/coworker) · repo · github.com · free
The creator's agent/bot tool. Version 0.7.0 adds a Primary Bot, free web search, an activity dashboard and support for open models through OpenRouter.
Also in: Coworker: a local-first desktop AI coworker that works with any model (Melvin Vivas on X · notes), Coworker: A Desktop AI Assistant App, Not a Coding Agent (Melvin Vivas on X · notes), Coworker v0.7.2: Open-Source Desktop AI Assistant (Melvin Vivas on X · notes), Coworker: an open-source desktop AI assistant with scheduled jobs (Melvin Vivas on X · notes) and 59 more
Try this
- Try LFM2.5-24B-A2B in a Colab notebook and check whether it fits on a T4 GPU.
- Run LFM2.5-24B-A2B locally inside an agent harness and test it on multi-step tasks.
More in LLM Fundamentals
- New Gemma Developer Documentation Site
- Grok Voice 3.0: xAI's Speech-to-Speech Model
- Is AI Getting Cheaper? How to Measure LLM Cost Per Task and Per Intelligence Level
- Muse Wonder vs Opus 5.5: Same Prompt, Very Different API Cost
- AI Engineer Vocab Quiz: 11 Acronyms to Know for Interviews
- Colab Notebook for Liquid AI's d1-3B Decision Model