{"slug": "liquid-ai-releases-lfm2-5-24b-a2b-a-2b-active-moe-for-on-device-agents", "title": "Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE for On-Device Agents", "summary": "Liquid AI released LFM2.5-24B-A2B, an open-weight 24B Mixture-of-Experts reasoning model with 2B active parameters aimed at on-device agents. The model scores 48.09 on LiveClaw and decodes 184 tokens/s on an Apple M5 Max.", "body_md": "Liquid AI released LFM2.5-24B-A2B, an open-weight 24B Mixture-of-Experts reasoning model with 2B active parameters. It targets local agents, scoring 48.09 on LiveClaw and decoding 184 tokens/s on an Apple M5 Max.\n\nThe post [Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE for On-Device Agents](https://www.marktechpost.com/2026/10/14/liquid-ai-lfm2-5-24b-a2b/) appeared first on [MarkTechPost](https://www.marktechpost.com).", "url": "https://wpnews.pro/news/liquid-ai-releases-lfm2-5-24b-a2b-a-2b-active-moe-for-on-device-agents", "canonical_source": "https://www.marktechpost.com/2026/10/14/liquid-ai-lfm2-5-24b-a2b/", "published_at": "2026-10-14 07:50:40+00:00", "updated_at": "2026-10-15 00:19:35.408071+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-agents", "ai-products"], "entities": ["Liquid AI", "LFM2.5-24B-A2B", "LiveClaw", "Apple M5 Max", "MarkTechPost"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/liquid-ai-releases-lfm2-5-24b-a2b-a-2b-active-moe-for-on-device-agents", "markdown": "https://wpnews.pro/news/liquid-ai-releases-lfm2-5-24b-a2b-a-2b-active-moe-for-on-device-agents.md", "text": "https://wpnews.pro/news/liquid-ai-releases-lfm2-5-24b-a2b-a-2b-active-moe-for-on-device-agents.txt", "jsonld": "https://wpnews.pro/news/liquid-ai-releases-lfm2-5-24b-a2b-a-2b-active-moe-for-on-device-agents.jsonld"}}