Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE for On-Device Agents
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 appea…
Read the full story at MarkTechPost ↗
Timeline · 1 report
- 2026-10-14 07:50 · MarkTechPost
Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE for On-Device Agents