# LLM Pruning and Distillation in Practice: The Minitron Approach

arXiv: https://arxiv.org/abs/2408.11796 · HTML: https://mlsanity.com/paper/2408.11796/

## Key facts

- Cited by 82 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 21 Aug 2024.

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning](https://mlsanity.com/paper/2310.06694/) (2023)
- [SliceGPT: Compress Large Language Models by Deleting Rows and Columns](https://mlsanity.com/paper/2401.15024/) (2024)
- [XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages](https://mlsanity.com/paper/2106.13822/) (2021)
- [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)
- [ChatQA: Surpassing GPT-4 on Conversational QA and RAG](https://mlsanity.com/paper/2401.10225/) (2024)
- [Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods](https://mlsanity.com/paper/2402.02834/) (2024)
- [Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models](https://mlsanity.com/paper/2407.07263/) (2024)
- [A deeper look at depth pruning of LLMs](https://mlsanity.com/paper/2407.16286/) (2024)

## Built on by (most cited first, 30 of 82)

- [SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer](https://mlsanity.com/paper/2501.18427/) (2025)
- [Ministral 3](https://mlsanity.com/paper/2601.08584/) (2026)
- [Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models](https://mlsanity.com/paper/2504.03624/) (2025)
- [RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models](https://mlsanity.com/paper/2412.07679/) (2024)
- [VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers](https://mlsanity.com/paper/2507.01016/) (2025)
- [Distillation Scaling Laws](https://mlsanity.com/paper/2502.08606/) (2025)
- [KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse](https://mlsanity.com/paper/2502.16002/) (2025)
- [Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition](https://mlsanity.com/paper/2505.22375/) (2025)
- [SAM Decoding: Speculative Decoding via Suffix Automaton](https://mlsanity.com/paper/2411.10666/) (2024)
- [The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective](https://mlsanity.com/paper/2506.04301/) (2025)
- [Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN](https://mlsanity.com/paper/2412.13795/) (2024)
- [Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games](https://mlsanity.com/paper/2506.03610/) (2025)
- [Pre-training Distillation for Large Language Models: A Design Space Exploration](https://mlsanity.com/paper/2410.16215/) (2024)
- [Inference-Time Hyper-Scaling with KV Cache Compression](https://mlsanity.com/paper/2506.05345/) (2025)
- [R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference](https://mlsanity.com/paper/2504.19449/) (2025)
- [Kanana: Compute-efficient Bilingual Language Models](https://mlsanity.com/paper/2502.18934/) (2025)
- [DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery](https://mlsanity.com/paper/2505.13940/) (2025)
- [DarwinLM: Evolutionary Structured Pruning of Large Language Models](https://mlsanity.com/paper/2502.07780/) (2025)
- [FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers](https://mlsanity.com/paper/2506.04213/) (2025)
- [Instruction-Following Pruning for Large Language Models](https://mlsanity.com/paper/2501.02086/) (2025)
- [CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs](https://mlsanity.com/paper/2505.13778/) (2025)
- [PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation](https://mlsanity.com/paper/2412.03409/) (2024)
- [Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models](https://mlsanity.com/paper/2412.13702/) (2024)
- [Neodragon: Mobile Video Generation using Diffusion Transformer](https://mlsanity.com/paper/2511.06055/) (2025)
- [LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trends](https://mlsanity.com/paper/2410.15281/) (2024)
- [VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models](https://mlsanity.com/paper/2412.01822/) (2024)
- [EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models](https://mlsanity.com/paper/2502.06663/) (2025)
- [Smoothing Out Hallucinations: Mitigating LLM Hallucination with Smoothed Knowledge Distillation](https://mlsanity.com/paper/2502.11306/) (2025)
- [FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data](https://mlsanity.com/paper/2507.10540/) (2025)
- [AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs](https://mlsanity.com/paper/2510.10467/) (2025)

## Abstract (arXiv)

We present a comprehensive report on compressing the Llama 3.1 8B and Mistral NeMo 12B models to 4B and 8B parameters, respectively, using pruning and distillation. We explore two distinct pruning strategies: (1) depth pruning and (2) joint hidden/attention/MLP (width) pruning, and evaluate the results on common benchmarks from the LM Evaluation Harness. The models are then aligned with NeMo Aligner and tested in instruct-tuned versions. This approach produces a compelling 4B model from Llama 3.1 8B and a state-of-the-art Mistral-NeMo-Minitron-8B (MN-Minitron-8B for brevity) model from Mistral NeMo 12B. We found that with no access to the original data, it is beneficial to slightly fine-tune teacher models on the distillation dataset. We open-source our base model weights on Hugging Face with a permissive license.