{"slug": "small-models-for-agentic-systems", "title": "Small Models for Agentic Systems", "summary": "LiquidAI's LFM 2.5 1.2B, a 1.2-billion-parameter model that is 696 MB on disk, can power agentic systems with modifications to an MCP server, according to a developer's test. The model required adding examples and removing a confusing tool, but it runs at over 300 tokens per second and uses minimal RAM, potentially eliminating the need for GPU upgrades for local agentic tasks.", "body_md": "Last night I spent some time trying to make my **MCP server** work with a **smaller local model**, one that is just 1.2 billion parameters and 696 MB on disk. This is LiquidAI's LFM 2.5 1.2B, with file name `LFM2.5-1.2B-Instruct-QAD-Q4_0.gguf`\n\n.\n\nMost small models I test fail too badly and I just **delete them** right away. However this model seemed to have some potential to work for my agentic system. It **required some changes** in the MCP server.\n\n• I had to add more examples and details about how to respond on certain user queries.\n\n• I had to remove a confusing tool (which it did not seem to understand, and would randomly call just to annoy me).\n\nSo basically I have a system with just **1 tool** that can be called in many different ways. The **small model** thus **does not get confused** about what it is supposed to do. It still gets confused by certain things: it has trouble keeping track of who said what, and what certain words mean in a phrase. However it runs at over 300 tokens per second, uses minimal RAM, and will make it so I basically will never need to update my GPU to run local agentic tasks (it even will run speedily on CPU alone).", "url": "https://wpnews.pro/news/small-models-for-agentic-systems", "canonical_source": "https://www.dotnetperls.com/2026_8_20_small-models-agentic-systems", "published_at": "2026-08-20 07:00:00+00:00", "updated_at": "2026-08-20 14:15:09.959190+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-tools"], "entities": ["LiquidAI", "LFM 2.5 1.2B", "MCP server"], "alternates": {"html": "https://wpnews.pro/news/small-models-for-agentic-systems", "markdown": "https://wpnews.pro/news/small-models-for-agentic-systems.md", "text": "https://wpnews.pro/news/small-models-for-agentic-systems.txt", "jsonld": "https://wpnews.pro/news/small-models-for-agentic-systems.jsonld"}}