LFM2.5 2.6b outperforms MiniCPM5 2b on small agentic tasks with tools, using less RAM and faster speed despite more parameters

I tried both these models on a few small agentic tasks with tools (i.e. "What's the weather like today?", etc.). They're both pretty solid at using web search to find answers despite being small models. TLDR: LFM2.5...