Liquid AI releases LFM2.5-24B-A2B for on-device agents

Name: Liquid AI's 24B open-weight model for on-device agents
Uploaded: 2026-10-14T00:00:00+05:30
Description: Open-weight 24B MoE with ~2B active params and 131K context. Liquid reports LiveClaw 48.09 vs Qwen3.6-35B's 38.19, AutomationBench 27.69 vs 8.72, 184 tok/s on Apple M5 Max, and 21K+ output tok/s on one NVIDIA B300.

Why it matters

Open-weight 24B MoE with ~2B active params and 131K context. Liquid reports LiveClaw 48.09 vs Qwen3.6-35B's 38.19, AutomationBench 27.69 vs 8.72, 184 tok/s on Apple M5 Max, and 21K+ output tok/s on one NVIDIA B300.

Read the source: Liquid AI (opens in a new tab)

Watch on YouTube Watch on Instagram

All hits from 14 Oct 2026 More Agents Get the daily hits by email