# Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization

arXiv: https://arxiv.org/abs/2509.23202 · HTML: https://mlsanity.com/paper/2509.23202/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 56 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 30 of 36)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [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)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [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)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [QuIP: 2-Bit Quantization of Large Language Models With Guarantees](https://mlsanity.com/paper/2307.13304/) (2023)
- [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)
- [Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning](https://mlsanity.com/paper/2208.11580/) (2022)
- [SqueezeLLM: Dense-and-Sparse Quantization](https://mlsanity.com/paper/2306.07629/) (2023)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [Extreme Compression of Large Language Models via Additive Quantization](https://mlsanity.com/paper/2401.06118/) (2024)
- [QTIP: Quantization with Trellises and Incoherence Processing](https://mlsanity.com/paper/2406.11235/) (2024)
- [Evaluating Quantized Large Language Models](https://mlsanity.com/paper/2402.18158/) (2024)
- [Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels](https://mlsanity.com/paper/2105.04522/) (2021)
- [8-Bit Approximations for Parallelism in Deep Learning](https://mlsanity.com/paper/1511.04561/) (2015)
- [Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study](https://mlsanity.com/paper/2307.08072/) (2023)
- ["Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization](https://mlsanity.com/paper/2411.02355/) (2024)

## Built on by (most cited first, 30 of 32)

- [Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery](https://mlsanity.com/paper/2601.20088/) (2026)
- [ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference](https://mlsanity.com/paper/2511.10645/) (2025)
- [WUSH: Near-Optimal Adaptive Transforms for LLM Quantization](https://mlsanity.com/paper/2512.00956/) (2025)
- [TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control](https://mlsanity.com/paper/2510.27527/) (2025)
- [Pushing the Limits of Block Rotations in Post-Training Quantization](https://mlsanity.com/paper/2601.22347/) (2026)
- [Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats](https://mlsanity.com/paper/2601.09555/) (2026)
- [OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization](https://mlsanity.com/paper/2605.17757/) (2026)
- [DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization](https://mlsanity.com/paper/2604.17789/) (2026)
- [BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization](https://mlsanity.com/paper/2603.16590/) (2026)
- [Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs](https://mlsanity.com/paper/2602.10377/) (2026)
- [FAAR: Format-Aware Adaptive Rounding for NVFP4](https://mlsanity.com/paper/2603.22370/) (2026)
- [Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs](https://mlsanity.com/paper/2605.20315/) (2026)
- [Optimal Post-Training Quantization Scales and Where to Find Them](https://mlsanity.com/paper/2606.10890/) (2026)
- [LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs](https://mlsanity.com/paper/2602.17681/) (2026)
- [Diagnosing FP4 inference: a layer-wise and block-wise sensitivity analysis of NVFP4 and MXFP4](https://mlsanity.com/paper/2603.08747/) (2026)
- [TACO: Efficient Communication Compression of Intermediate Tensors for Scalable Tensor-Parallel LLM Training](https://mlsanity.com/paper/2604.24088/) (2026)
- [Quantizing Recursive Reasoning Models](https://mlsanity.com/paper/2607.16237/) (2026)
- [FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling](https://mlsanity.com/paper/2608.01847/) (2026)
- [TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly](https://mlsanity.com/paper/2603.19296/) (2026)
- [Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate](https://mlsanity.com/paper/2604.13806/) (2026)
- [Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor](https://mlsanity.com/paper/2605.20402/) (2026)
- [Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V](https://mlsanity.com/paper/2605.27003/) (2026)
- [GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation](https://mlsanity.com/paper/2606.01412/) (2026)
- [AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation](https://mlsanity.com/paper/2604.02525/) (2026)
- [Not All NVFP4 QAT Recipes Are Equal: How Architecture and Scale Shape Model Quality for Anomaly Segmentation](https://mlsanity.com/paper/2605.27616/) (2026)
- [SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference](https://mlsanity.com/paper/2606.26587/) (2026)
- [PRQuant: Permutation Residual Quantization for Low-Overhead Inference](https://mlsanity.com/paper/2609.22106/) (2026)
- [Disaggregated Quantization: Specializing LLM Prefill and Decode](https://mlsanity.com/paper/2609.26333/) (2026)
- [LLMs are General Asynchronous Agents](https://mlsanity.com/paper/2609.35427/) (2026)
- [Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference](https://mlsanity.com/paper/2609.36654/) (2026)

## Abstract (arXiv)

The recent hardware-accelerated microscaling 4-bit floating-point formats such as MXFP4 and NVFP4, supported on NVIDIA and AMD GPUs, promise to revolutionize large language model (LLM) inference. Yet, their practical benefits remain unproven. We present the first comprehensive study of MXFP4 and NVFP4 for post-training quantization, revealing gaps between their promise and real-world performance. Our analysis shows that state-of-the-art methods struggle with FP4, due to two key issues: (1) NVFP4's small group size provably neutralizes traditional outlier mitigation techniques; (2) MXFP4's power-of-two scale quantization severely degrades accuracy due to high induced error. To bridge this gap, we introduce Micro-Rotated-GPTQ (MR-GPTQ), a variant of the classic GPTQ quantization algorithm that tailors the quantization process to FP4's unique properties, by using block-wise Hadamard transforms and format-specific optimizations. We support our proposal with a set of high-performance GPU kernels that enable the MR-GPTQ format with negligible overhead, by rotation fusion into the weights, and fast online computation of the activations. This leads to speedups vs. FP16 of up to 3.6x layer-wise, and 2.2x end-to-end on NVIDIA B200, and of 6x layer-wise and 4x end-to-end on RTX5090. Our extensive empirical evaluation demonstrates that MR-GPTQ matches or outperforms state-of-the-art accuracy, significantly boosting MXFP4, to the point where it can near the accuracy that of NVFP4. We conclude that, while FP4 is not an automatic upgrade over INT4, format-specialized methods like MR-GPTQ can unlock a new frontier of accuracy-performance trade-offs.