Liquid AI Says LFM2.5-24B-A2B Beats Qwen3.6-35B-A3B on Five Agentic Benchmarks
Summary
Liquid AI releases LFM2.5-24B-A2B, a 24B-parameter reasoning model with 2B active parameters for on-device agents. The company says it leads or matches Qwen3.6-35B-A3B on five of eight agentic benchmarks, scoring 27.69 on AutomationBench versus 8.72. The open-weight model decodes 184 tokens/s on an Apple M5 Max.
Key Points
- Liquid AI says LFM2.5-24B-A2B reaches over 21K output tokens per second on a single NVIDIA B300 GPU.
- Liquid Console charges $0.10 per 1M input tokens for LFM2.5-24B-A2B API inference.
- The model extends its context window to 131,072 tokens from 32,768 in the prior LFM2-24B-A2B.