# Block-Level Weight-Space Structure Persists Under Post-Training: An Empirical Study Across LLM Families

arXiv: https://arxiv.org/abs/2609.26147 · HTML: https://mlsanity.com/paper/2609.26147/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 20 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [Git Re-Basin: Merging Models modulo Permutation Symmetries](https://mlsanity.com/paper/2209.04836/) (2022)
- [The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks](https://mlsanity.com/paper/2110.06296/) (2021)
- [S-LoRA: Serving Thousands of Concurrent LoRA Adapters](https://mlsanity.com/paper/2311.03285/) (2023)
- [Punica: Multi-Tenant LoRA Serving](https://mlsanity.com/paper/2310.18547/) (2023)
- [DeltaZip: Efficient Serving of Multiple Full-Model-Tuned LLMs](https://mlsanity.com/paper/2312.05215/) (2023)
- [Generalized Linear Mode Connectivity for Transformers](https://mlsanity.com/paper/2506.22712/) (2025)
- [Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs](https://mlsanity.com/paper/2508.00161/) (2025)
- [ZipLLM: Efficient LLM Storage via Model-Aware Synergistic Data Deduplication and Compression](https://mlsanity.com/paper/2505.06252/) (2025)

## Abstract (arXiv)

Modern LLMs are deployed as families of post-trained variants (base, instruct, chat, code) derived from a shared set of pre-trained weights. We present an empirical study of how post-training transforms weight-space geometry, covering eight configurations across four architecture families (Qwen2.5, Llama-3.1/3.2, Mistral, Gemma-2). We identify a granularity gap: post-training modifies every tensor (zero of 291-339 tensors remain byte-identical, so hash-based deduplication achieves 0% savings), yet preserves block-level structure (mean cosine similarity exceeds 0.99 and relative Frobenius distance stays below 0.13). Post-training therefore acts as a structured perturbation that shifts every parameter while leaving block-level geometry intact. The property is not universal: independently trained specializations (for example, Qwen2.5-Coder) attain cosine similarity around 0.64 with the general base, indicating a disconnected region of weight space. Perturbation magnitude varies systematically with model scale, architecture family, and post-training recipe. As a practical application, we build LinkerLLM, a lazy loader that aliases shareable blocks across co-resident variants, achieving 18-48% GPU memory savings and enabling up to five 7B-parameter variants on a single 24 GB consumer GPU. Five of eight configurations retain at least 94% of the unshared variant's quality on MMLU, ARC-Challenge, HellaSwag, and WinoGrande; the remaining three (Mistral-7B, Gemma-2-2B, Llama-3.2-1B) have one below-threshold benchmark each (87-91%), which we report transparently rather than gate the block-sharing decision on a single threshold.