{"slug": "lfm-2-5-agentic-model-for-tool-calling", "title": "LFM 2.5 Agentic Model for Tool Calling", "summary": "Liquid AI released LFM 2.5, an 8-billion-parameter agentic model with 1 billion active parameters focused exclusively on tool calling, achieving nearly 200 tokens per second on a GPU. The model excels at routing users to appropriate MCP tools but is not suitable for complex text analysis or general-purpose tasks.", "body_md": "Large and powerful **LLMs** are great, but sometimes a **smaller**, **local model** is sufficient. For example, with an MCP server, a small local model can call tools and be used to accomplish things. I continued to search for small agentic models and found **LFM 2.5**.\n\nThis is a model created by **Liquid AI**, an American company, and it is focused on **agentic tool calling**. I downloaded the `LFM2.5-8B-A1B-UD-Q4_K_XL.gguf`\n\nfile and tested in `llama-cpp`\n\n.\n\nBasically this model is focused on **tool calling** exclusively. This means:\n\n• For complex analysis of text, LFM is not a good choice.\n\n• For trying to create a customer service AI system, where users indicate what their problem is, and the model routes them to the appropriate MCP tools, it is a good choice.\n\nI found that with a few more MCP server tools, I could get LFM 2.5 to **find available tools** and then **call them** based on my messages. The model has 8 billion parameters, but only 1 billion active, so it is **extremely fast**—I get nearly 200 tokens per second with a GPU, and it even works acceptably without a GPU. I have found LFM 2.5 to be an excellent agentic tool calling model, but beyond that, a larger model would be needed.", "url": "https://wpnews.pro/news/lfm-2-5-agentic-model-for-tool-calling", "canonical_source": "https://www.dotnetperls.com/2026_7_29_lfm-25-agentic-model-tool-calling", "published_at": "2026-07-29 07:00:00+00:00", "updated_at": "2026-07-29 16:14:21.758195+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-tools"], "entities": ["Liquid AI", "LFM 2.5", "llama-cpp", "MCP"], "alternates": {"html": "https://wpnews.pro/news/lfm-2-5-agentic-model-for-tool-calling", "markdown": "https://wpnews.pro/news/lfm-2-5-agentic-model-for-tool-calling.md", "text": "https://wpnews.pro/news/lfm-2-5-agentic-model-for-tool-calling.txt", "jsonld": "https://wpnews.pro/news/lfm-2-5-agentic-model-for-tool-calling.jsonld"}}