M Lewis, Sohir Maskey, Douglas Orr, Constantin Eichenberg, L Van Der Maaten, De Oliveira, M Hassan, K Li, M Singh, Johannes Messner
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Quantization-aware training (QAT) is an effective method to drastically reduce the memory footprint of LLMs while keeping performance degradation at an acceptable level. However, the optimal choice of quantization format and bitwidth presents a challenge in practice. The full design space of quantization is not fully explored in the context of QAT, and the precise trade-off between quantization and downstream performance is poorly understood, as comparisons often rely solely on perplexity-based evaluations. In this work, we address these shortcomings with an empirical study of QAT in the low-bit regime. We show that k-means based weight quantization outperforms integer formats and can be implemented efficiently on standard hardware. Furthermore, we find that, under a fixed inference memory budget, the best performance on generative downstream tasks is achieved with 1-bit quantized weights.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2602.15563")
get_code_for_paper("2602.15563")
have("2602.15563")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2602.15563.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2602.15563)
Connect an agent — have() is free.