LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation

LiquidAI releases Q4_0 GGUF checkpoints for LFM2.5 models using Quantization-Aware Distillation. These artifacts allow developers to run smaller models on edge hardware with near-full precision accuracy. Benchmarks show recovery of 97 percent of performance lost to standard quantization, enabling efficient inference on Raspberry Pi and mobile devices.