AIHacker Newsabout 3 hours ago
Liquid AI Releases Fast On-Device AI Model
6 min read
Liquid AI releases LFM2.5-24B-A2B, a 24B-parameter reasoning model with 2B active parameters, today. It scores 48.09 on LiveClaw versus 38.19 for Qwen3.6-35B-A3B and runs up to 1.7 times faster than comparable MoEs on-device. The model is open-weight and available on Hugging Face for local deployment across Apple, AMD, and Nvidia hardware.
Level
Hype check
Tap to vote and see what everyone thinks.
