src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" alt="Liquid AI" LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning. Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-2.6B Example usage with llama.cpp: The Quantization-Aware Distillation (QAD) checkpoint is available as This is distinct from the post-training-quantized LFM2.5-2.6B-Q40.gguf; both use the GGUF Q40 format.