# PocketLLM: Ultimate Compression of Large Language Models via Meta Networks

arXiv: https://arxiv.org/abs/2511.17637 · HTML: https://mlsanity.com/paper/2511.17637/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 19 Nov 2025.

## Builds on (most cited first, 19 of 19)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [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)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks](https://mlsanity.com/paper/2402.04396/) (2024)
- [SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression](https://mlsanity.com/paper/2306.03078/) (2023)
- [Extreme Compression of Large Language Models via Additive Quantization](https://mlsanity.com/paper/2401.06118/) (2024)
- [DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs](https://mlsanity.com/paper/2406.01721/) (2024)
- [QTIP: Quantization with Trellises and Incoherence Processing](https://mlsanity.com/paper/2406.11235/) (2024)
- [A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset](https://mlsanity.com/paper/1806.00358/) (2018)
- [Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization](https://mlsanity.com/paper/2405.10616/) (2024)
- [Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding](https://mlsanity.com/paper/2503.10135/) (2025)
- [SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning](https://mlsanity.com/paper/2508.15212/) (2025)
- [SLMQuant:Benchmarking Small Language Model Quantization for Practical Deployment](https://mlsanity.com/paper/2511.13023/) (2025)

## Built on by (most cited first, 3 of 3)

- [Saliency-Aware Regularized Quantization Calibration for Large Language Models](https://mlsanity.com/paper/2605.05693/) (2026)
- [Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions](https://mlsanity.com/paper/2605.07271/) (2026)
- [BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression](https://mlsanity.com/paper/2607.08643/) (2026)

## Abstract (arXiv)

As Large Language Models (LLMs) continue to grow in size, storing and transmitting them on edge devices becomes increasingly challenging. Traditional methods like quantization and pruning struggle to achieve extreme compression of LLMs without sacrificing accuracy. In this paper, we introduce PocketLLM, a novel approach to compress LLMs in a latent space via meta-networks. A simple encoder network is proposed to project the weights of LLMs into discrete latent vectors, which are then represented using a compact codebook. A lightweight decoder network is employed to map the codebook's representative vectors back to the original weight space. This method allows for significant compression of the large weights in LLMs, consisting solely of a small decoder, a concise codebook, and an index. Extensive experiments show that PocketLLM achieves superior performance even at significantly high compression ratios, e.g., compressing Llama 2-7B by 10x with a negligible drop in accuracy.