LFM 2.5 2.6B is the best small model for tool use I have ever used.
Summary
The author praises LFM 2.5 2.6B as the best small model for tool use they've used, noting that it works nearly to spec without additional training in their local AI search project.
Similar Articles
LFM 2.6B is a lot of fun.
The author shares hands-on experience with LFM 2.6B, a small model designed for phones, praising its speed and usefulness for quick tasks like summarization and autocomplete, though it has a 128k context limit.
New LFM2.5 8b A1b model!!
Introducing LFM2.5 8b A1b, a new AI model with performance on par with Nemotron 3 Nano but at higher speed. Support is being added to SmallCode for non-standard tool calls.
LFM2.5-2.6B is out
Liquid AI released LFM2.5-2.6B, a new tiny model focused on agentic capabilities. The author is excited to test it for high-volume tasks like document summarization.
LFM2.5 2.6b vs MiniCPM5 2b
作者在 M1 Air 上使用 llama-server 对比了 LFM2.5 2.6B 与 MiniCPM5 2B 在小型 agentic 工具调用任务上的表现。结论是 LFM2.5 明显更优——尽管参数更多但速度更快、内存占用更低，而 MiniCPM5 虽然在 agentic 任务上可能更强，但常常在英文提问下返回中文。
@noctus91: I recently switched from Qwen 3.5 9B to LFM2.5-8B-A1B by @liquidai, and it's quickly become my default local model in H…
A user shares their positive experience switching from Qwen 3.5 9B to Liquid AI's new LFM2.5-8B-A1B model, praising its speed and reliability for agentic tasks while noting coding remains a weakness. The model is an 8B MoE with 1.5B active parameters and 128K context, optimized for devices and server-side use.