Liquid AI Launches LFM2.5-24B-A2B, a 24B-Parameter Local Inference Model

iconKuCoinFlash
Share
AI summary iconSummary
Liquid AI has launched LFM2.5-24B-A2B, a 24-billion-parameter model designed for local inference. Built on MetaEra, it runs on laptops and PCs and handles multi-step tasks within agent frameworks. The model activates 2.45 billion parameters per token and supports a 131K-token context window. Weights are available on Hugging Face with llama.cpp support. This update brings fresh AI and crypto news, highlighting on-chain developments in model deployment.
ME AI announcement: Liquid AI has released LFM2.5-24B-A2B, the largest member of the LFM2.5 series, designed as a locally efficient model that can run on laptops and PCs and perform multi-step tasks within mainstream agent harnesses. The model has a total of 24B parameters and activates 2.45B per token (another source states 2B active per token), with a context window extended to 131K tokens. Base and post-training weights are available on Hugging Face and support llama.cpp. (Source: InFoQ)
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information. Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.