From the source
Liquid AI released LFM2.5-2.6B, a 2.6 billion parameter model designed for on-device agentic workloads such as planning, tool calling, and multi-step tasks.
The model is pre-trained on approximately 34 trillion tokens, supports a 128K token context window, and is available on Hugging Face in both base and post-trained versions.
Benchmarks show it is competitive with models nearly four times its size on STEM, instruction following, tool use, and agentic tasks.
