Get the app
Machine LearningAgents5 min reading time

Run fast, private agents on-device with LFM2.5-24B-A2B

Hugging Face
Read the full article
LFM2.5-24B-A2B is a 24B-parameter reasoning model activating only 2B parameters per token, enabling fast, private on-device agents that outperform larger models on agentic tasks. It supports long contexts up to 131K tokens and integrates with popular agent frameworks.
#agentic-software-development#hermes-agent#lfm2-5-24b-a2b#openclaw#pi#qwen3-6-35b-a3b

More in Machine Learning

Machine Learning1 min read

Fortnite-maker Epic Games confirms 'huge pivot' towards using AI

Covered by 4 sources
Machine Learning14 min read

All Systems Go: Global PC App Ecosystem Ready for NVIDIA RTX Spark

Nvidia Blog
Machine Learning2 min read

Anthropic says small AI models may soon copy themselves onto smart devices

Covered by 2 sources