# Compressing LLMs with MoP: Mixture of Pruners

arXiv: https://arxiv.org/abs/2602.06127 · HTML: https://mlsanity.com/paper/2602.06127/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 38 of its 48 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Builds on (most cited first, 30 of 38)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [SliceGPT: Compress Large Language Models by Deleting Rows and Columns](https://mlsanity.com/paper/2401.15024/) (2024)
- [LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models](https://mlsanity.com/paper/2407.12772/) (2024)
- [The Unreasonable Ineffectiveness of the Deeper Layers](https://mlsanity.com/paper/2403.17887/) (2024)
- [Compact Language Models via Pruning and Knowledge Distillation](https://mlsanity.com/paper/2407.14679/) (2024)
- [LaCo: Large Language Model Pruning via Layer Collapse](https://mlsanity.com/paper/2402.11187/) (2024)
- [Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models](https://mlsanity.com/paper/2403.03003/) (2024)
- [Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods](https://mlsanity.com/paper/2402.02834/) (2024)
- [LLM Pruning and Distillation in Practice: The Minitron Approach](https://mlsanity.com/paper/2408.11796/) (2024)
- [Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models](https://mlsanity.com/paper/2405.14297/) (2024)
- [The LLM Surgeon](https://mlsanity.com/paper/2312.17244/) (2023)
- [Streamlining Redundant Layers to Compress Large Language Models](https://mlsanity.com/paper/2403.19135/) (2024)
- [DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models](https://mlsanity.com/paper/2410.11988/) (2024)
- [LOVA3: Learning to Visual Question Answering, Asking and Assessment](https://mlsanity.com/paper/2405.14974/) (2024)

## Abstract (arXiv)

The high computational demands of Large Language Models (LLMs) motivate methods that reduce parameter count and accelerate inference. In response, model pruning emerges as an effective strategy, yet current methods typically focus on a single dimension-depth or width. We introduce MoP (Mixture of Pruners), an iterative framework that unifies these dimensions. At each iteration, MoP generates two branches-pruning in depth versus pruning in width-and selects a candidate to advance the path. On LLaMA-2 and LLaMA-3, MoP advances the frontier of structured pruning, exceeding the accuracy of competing methods across a broad set of compression regimes. It also consistently outperforms depth-only and width-only pruning. Furthermore, MoP translates structural pruning into real speedup, reducing end-to-end latency by 39% at 40% compression. Finally, extending MoP to the vision-language model LLaVA-1.5, we notably improve computational efficiency and demonstrate that text-only recovery fine-tuning can restore performance even on visual tasks.