Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE for On-Device Agents
Quick Answer
Liquid AI has launched LFM2.5-24B-A2B, a 24B Mixture-of-Experts model featuring 2B active parameters, optimized for on-device agents.
Quick Take
It achieves a score of 48.09 on LiveClaw and decodes at 184 tokens/s on the Apple M5 Max, enhancing local AI capabilities.
Key Points
- LFM2.5-24B-A2B features 2B active parameters for enhanced performance.
- Achieves a benchmark score of 48.09 on LiveClaw.
- Decodes 184 tokens per second on Apple M5 Max.
- Designed specifically for agents.
- allows for flexible deployment.
Article Excerpt
From source RSS / original summaryLiquid 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. The post Liquid AI Releases LFM2. 5-24B-A2B: A 2B-Active MoE for On-Device Agents appeared first on MarkTechPost.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from MarkTechPost
See more →Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model
Microsoft has launched Microsoft-Decision-1, a decision-scoring model derived from Alibaba's Qwen3.5-9B. This model focuses on routing, classification, verification, and agent control, providing calibrated probabilities for fixed answer options instead of generating text. It is now available in Microsoft Foundry and OpenRouter.