Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE for On-Device Agents
MarkTechPosten
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. The post Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE for On-Device Agents appeared first on MarkTechPost .
This is a short summary published by AI Global Wire. The full article is owned and hosted by MarkTechPost — open it there to read it in full.
Read the full story at MarkTechPost- Verktyg
- Agenter
- Reglering
Related AI news
- SolarWinds’ Avior pairs AI agents with deterministic execution for enterprise ITSiliconANGLE · October 14, 2026
- Jensen Huang says Nvidia is pledging $250M in accelerated computing resources over five years to fund UK AI security and agentic safety research (Reuters)Techmeme · October 14, 2026
- Apple bets AI can finally make us want a smart homeAxios · October 14, 2026
- Lenovo expands AI security offering in Singapore, APACTech in Asia · October 14, 2026
- Exclusive: AI safety money floods into political racesAxios · October 14, 2026
- 9 Best AI Gateways in 2026: Bifrost, Portkey, LiteLLM, Kong and 5 More RankedMarkTechPost · October 14, 2026