GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets

arXiv:2605.18475v1 Announce Type: cross Abstract: Mixed-precision quantization improves the budget--accuracy trade-off for large language models (LLMs) by allocating more bits to sensitive modules. However, automating this allocation at LLM scale faces a unique combination of constraints: learnable approaches require quantization-aware training, which is infeasible for billion-parameter models; training-free alternatives rely on static proxy metrics that miss cross-module interactions and must b