Every LFM2.5-24B-A2B story collected by The AI Daily, 2 so far, newest first, refreshed hourly.
User Impressed with LFM2.5-24B-A2B in Pi AgentA user tested LiquidAI's new LFM2.5-24B-A2B model, finding it stable when replacing existing models in Pi Agent workflows. It achieved ~95 tokens per second sustained on an AMD W7900 with llama.cpp, using 30GB VRAM at Q8 quantization with full 128k context, suitable as a companion smaller model.
LFM2.5-24B-A2B: fast, private on-device agentsHugging Face released LFM2.5-24B-A2B, a 24B-parameter model with only 2B active parameters for on-device agents. It supports 131K context and tool use, runs at 184 tok/s on Apple M5 Max and up to 21K output tok/s on an NVIDIA B300 GPU, and scores 48.09 on LiveClaw versus Qwen3.6-35B-A3B's 38.19.
The A.I. Daily