Expanded‑rank ternary decomposition pushes LLM PTQ to near‑bf16 accuracy
ExTernD decomposes weight matrices into two ternary factors with a diagonal scaling vector, expanding the inner rank beyond full rank, which lets accuracy approach any quantization level. It hits Q4‑level performance at just 5‑5.5 effective bits per weight on Gemma‑4‑E2B and Qwen‑3.5‑4B, closing the gap to bf16 without retraining.