# Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery

arXiv: https://arxiv.org/abs/2601.20088 · HTML: https://mlsanity.com/paper/2601.20088/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 45 of its 60 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)

## Builds on (most cited first, 30 of 45)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models](https://mlsanity.com/paper/2305.07895/) (2023)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models](https://mlsanity.com/paper/2308.13137/) (2023)
- [QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks](https://mlsanity.com/paper/2402.04396/) (2024)
- [LLM-QAT: Data-Free Quantization Aware Training for Large Language Models](https://mlsanity.com/paper/2305.17888/) (2023)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [FP8 Formats for Deep Learning](https://mlsanity.com/paper/2209.05433/) (2022)
- [Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation](https://mlsanity.com/paper/2004.09602/) (2020)
- [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](https://mlsanity.com/paper/2411.05007/) (2024)
- [Towards Understanding Knowledge Distillation](https://mlsanity.com/paper/2105.13093/) (2021)
- [Microscaling Data Formats for Deep Learning](https://mlsanity.com/paper/2310.10537/) (2023)
- [FlatQuant: Flatness Matters for LLM Quantization](https://mlsanity.com/paper/2410.09426/) (2024)

## Built on by (most cited first, 22 of 22)

- [BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization](https://mlsanity.com/paper/2603.16590/) (2026)
- [Bielik-Minitron-7B: Compressing Large Language Models via Structured Pruning and Knowledge Distillation for the Polish Language](https://mlsanity.com/paper/2603.11881/) (2026)
- [Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control](https://mlsanity.com/paper/2605.07182/) (2026)
- [Magpie: Real-Time World Renderer for Interactive Games](https://mlsanity.com/paper/2608.27168/) (2026)
- [Laguna M.1/XS.2 Technical Report](https://mlsanity.com/paper/2605.27605/) (2026)
- [Apertus LLM Family Expansion via Distillation and Quantization](https://mlsanity.com/paper/2605.29128/) (2026)
- [Characterizing the Impact of NVFP4 Quantization for Low-Power Edge AI Deployment](https://mlsanity.com/paper/2606.06527/) (2026)
- [QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction](https://mlsanity.com/paper/2608.13966/) (2026)
- [QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs](https://mlsanity.com/paper/2609.39223/) (2026)
- [Direction-Preserving Number Representations](https://mlsanity.com/paper/2605.07662/) (2026)
- [Nano-U: Efficient Terrain Segmentation for Tiny Robot Navigation](https://mlsanity.com/paper/2605.10210/) (2026)
- [FTerViT: Fully Ternary Vision Transformer](https://mlsanity.com/paper/2605.21171/) (2026)
- [Beyond Output Matching: Preserving Internal Geometry in NVFP4 LLM Distillation](https://mlsanity.com/paper/2606.05682/) (2026)
- [SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices](https://mlsanity.com/paper/2606.07098/) (2026)
- [Quantize the Target, Quantize the Drafter: Efficient Inference with Qwen3.5-4B](https://mlsanity.com/paper/2607.04244/) (2026)
- [Studying quantization trade-offs for efficient inference deployment in machine translation](https://mlsanity.com/paper/2607.29397/) (2026)
- [Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs](https://mlsanity.com/paper/2608.20953/) (2026)
- [Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs](https://mlsanity.com/paper/2608.21134/) (2026)
- [Disaggregated Quantization: Specializing LLM Prefill and Decode](https://mlsanity.com/paper/2609.26333/) (2026)
- [Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference](https://mlsanity.com/paper/2609.36654/) (2026)
- [LatentQuant: Preserving the Policy-Facing Latent Contract under NVFP4 VAE Quantization](https://mlsanity.com/paper/2610.03959/) (2026)
- [Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning](https://mlsanity.com/paper/2610.05745/) (2026)

## Abstract (arXiv)

This technical report presents quantization-aware distillation (QAD) and our best practices for recovering accuracy of NVFP4-quantized large language models (LLMs) and vision-language models (VLMs). QAD distills a full-precision teacher model into a quantized student model using a KL divergence loss. While applying distillation to quantized models is not a new idea, we observe key advantages of QAD for today's LLMs: 1. It shows remarkable effectiveness and stability for models trained through multi-stage post-training pipelines, including supervised fine-tuning (SFT), reinforcement learning (RL), and model merging, where traditional quantization-aware training (QAT) suffers from engineering complexity and training instability; 2. It is robust to data quality and coverage, enabling accuracy recovery without full training data. We evaluate QAD across multiple post-trained models including AceReason Nemotron, Nemotron 3 Nano, Nemotron Nano V2, Nemotron Nano V2 VL (VLM), and Llama Nemotron Super v1, showing consistent recovery to near-BF16 accuracy.