LFM2.5-2.6B on a OnePlus 13 at 17 tok/s ~ Pure CPU
英文标题：LFM2.5-2.6B on a OnePlus 13 at 17 tok/s ~ Pure CPU
As you all know the model is 2.69B parameters with a 128K context window and purpose-built for multi-step agent workflows. What you are seeing is the Q4_K_M GGUF running on my own inference engine built from scratch. The TUI is my own device probe suite running through ADB (Android Debug Bridg
打开原文相关 7 · 机会 2
中文
As you all know the model is 2.69B parameters with a 128K context window and purpose-built for multi-step agent workflows. What you are seeing is the Q4_K_M GGUF running on my own inference engine built from scratch. The TUI is my own device probe suite running through ADB (Android Debug Bridg
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
As you all know the model is 2.69B parameters with a 128K context window and purpose-built for multi-step agent workflows. What you are seeing is the Q4_K_M GGUF running on my own inference engine built from scratch. The TUI is my own device probe suite running through ADB (Android Debug Bridg