# Global Ranks Survive, Selected Heads Shift: BOS-Sink Topology under 4-bit Weight-Only Quantization

arXiv: https://arxiv.org/abs/2609.23585 · HTML: https://mlsanity.com/paper/2609.23585/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 13 references that are in the map.
- First posted on arXiv 20 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Massive Activations in Large Language Models](https://mlsanity.com/paper/2402.17762/) (2024)
- [When Attention Sink Emerges in Language Models: An Empirical View](https://mlsanity.com/paper/2410.10781/) (2024)
- [Why do LLMs attend to the first token?](https://mlsanity.com/paper/2504.02732/) (2025)
- [Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs](https://mlsanity.com/paper/2410.13835/) (2024)
- [Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization](https://mlsanity.com/paper/2406.12016/) (2024)
- [What are you sinking? A geometric approach on attention sink](https://mlsanity.com/paper/2508.02546/) (2025)
- [SinkTrack: Attention Sink based Context Anchoring for Large Language Models](https://mlsanity.com/paper/2604.10027/) (2026)

## Abstract (arXiv)

Sink-aware deployment may identify important first-token attention heads before a model is quantized, then reuse that map at the edge. We test when this shortcut is safe for 4-bit NF4 weight-only post-training quantization (PTQ). Our Sink Topology Consistency (STC) metrics separate global rank preservation, top-k set overlap, and layerwise sink-mass shift, and distinguish per-input sensitivity from calibration-map transfer. Across Qwen2.5-0.5B, Qwen2.5-1.5B, and Llama-3.2-1B, global bf16-to-4-bit ranks remain high at 4,096 tokens (ρs ≥ 0.980), yet top-k Jaccard overlap is only 0.619-0.793, corresponding to 76.5-88.5% membership retention. The global statistic also masks local failures: terminal Qwen layers shift by 6.2-7.9x their model means, whereas Llama-3.2-1B shows low, nearly uniform drift. Under a C4-to-LongBench shift, cross-domain overlap degrades more than the within-domain precision comparison for both Qwen models, but not for Llama-3.2-1B. Matched-domain 4-bit recalibration reaches 90% of a split-half stability plateau at the smallest tested n=8 for both Qwen models and n=32 for Llama-3.2-1B, though not as a sharp threshold; for the two Qwen models, updating only selected layers does not reach the full-map stability criterion. On Jetson Orin NX, the 16-sample workload takes seconds for the two models with valid on-device sink measurements. The practical message is precise: global rankings often transfer, but discrete head sets, layer-local policies, and cross-domain calibration should be revalidated after quantization.