Machine Heart
May 25, 2026 · Artificial Intelligence
EdgeRazor Delivers 15× Faster Decoding on PC & Mobile, Solving Low-Bit Collapse
EdgeRazor, an open‑source framework from Nanjing University and Microsoft AI, uses mixed‑precision quantization‑aware distillation to compress large language models to as low as 1.58‑bit, achieving up to 15× faster decoding on PC and mobile, 10× fewer training tokens, and 7× model size reduction while preserving benchmark performance.
LLM QuantizationModel Compressionedge deployment
0 likes · 12 min read