SEP 3, 2026 · PREPRINT
Scale-QLoRA: Code-Invariant Adapter Merging for Native 4-bit Microscaling LLMs
arXiv
This is a technical methods paper describing a novel algorithm for adapter merging in quantized language models, with empirical validation across four models and tasks, but without peer review, clinical outcomes, or comparison to established baselines sufficient to establish superiority.
Reported
Accuracy loss from naive mergingup to 39 pp
Training time speedup (8B dense m…3.9x
Task swap speedup~125x