# "Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization

arXiv: https://arxiv.org/abs/2411.02355 · HTML: https://mlsanity.com/paper/2411.02355/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## Builds on (most cited first, 20 of 20)

- [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)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [SqueezeLLM: Dense-and-Sparse Quantization](https://mlsanity.com/paper/2306.07629/) (2023)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving](https://mlsanity.com/paper/2405.04532/) (2024)
- [MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning](https://mlsanity.com/paper/2310.16049/) (2023)
- [Platypus: Quick, Cheap, and Powerful Refinement of LLMs](https://mlsanity.com/paper/2308.07317/) (2023)
- [ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation](https://mlsanity.com/paper/2303.08302/) (2023)
- [LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit](https://mlsanity.com/paper/2405.06001/) (2024)

## Built on by (most cited first, 30 of 34)

- [Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization](https://mlsanity.com/paper/2509.23202/) (2025)
- [The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm](https://mlsanity.com/paper/2507.18553/) (2025)
- [WUSH: Near-Optimal Adaptive Transforms for LLM Quantization](https://mlsanity.com/paper/2512.00956/) (2025)
- [Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis](https://mlsanity.com/paper/2502.13178/) (2025)
- [Does quantization affect models' performance on long-context tasks?](https://mlsanity.com/paper/2505.20276/) (2025)
- [Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats](https://mlsanity.com/paper/2601.09555/) (2026)
- [The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility](https://mlsanity.com/paper/2605.19537/) (2026)
- [When LLMs get significantly worse: A statistical approach to detect model degradations](https://mlsanity.com/paper/2602.10144/) (2026)
- [Statistically-Lossless Quantization of Large Language Models](https://mlsanity.com/paper/2605.02404/) (2026)
- [Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs](https://mlsanity.com/paper/2602.10377/) (2026)
- [OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature](https://mlsanity.com/paper/2505.22945/) (2025)
- [Edge Deployment of Small Language Models, a comprehensive comparison of CPU, GPU and NPU backends](https://mlsanity.com/paper/2511.22334/) (2025)
- [ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling](https://mlsanity.com/paper/2601.21198/) (2026)
- [The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs](https://mlsanity.com/paper/2607.08734/) (2026)
- [MatGPTQ: Efficient and Accurate Inference over Nested Quantized Models](https://mlsanity.com/paper/2602.03537/) (2026)
- [Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results](https://mlsanity.com/paper/2606.14516/) (2026)
- [Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment](https://mlsanity.com/paper/2606.19558/) (2026)
- [Designing Synthetic Discussion Generation Systems: A Case Study for Online Facilitation](https://mlsanity.com/paper/2503.16505/) (2025)
- [Float8@2bits: Entropy Coding Enables Data-Free Model Compression](https://mlsanity.com/paper/2601.22787/) (2026)
- [FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference](https://mlsanity.com/paper/2603.14591/) (2026)
- [QuantClaw: Precision Where It Matters for OpenClaw](https://mlsanity.com/paper/2604.22577/) (2026)
- [OffQ: Taming Structured Outliers in LLM Quantization by Offsetting](https://mlsanity.com/paper/2606.07116/) (2026)
- [IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier](https://mlsanity.com/paper/2609.10494/) (2026)
- [Optimizing AI Inference Across the Deployment Stack](https://mlsanity.com/paper/2609.10550/) (2026)
- [CienaLLM: Generative Climate-Impact Extraction from News Articles with Autoregressive LLMs](https://mlsanity.com/paper/2512.19305/) (2025)
- [Balancing Sustainability And Performance: The Role Of Small-Scale LLMs In Agentic Artificial Intelligence Systems](https://mlsanity.com/paper/2601.19311/) (2026)
- [LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation](https://mlsanity.com/paper/2604.19167/) (2026)
- [K-Quantization and its Impact on Output Performance](https://mlsanity.com/paper/2605.19645/) (2026)
- [Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving](https://mlsanity.com/paper/2609.04748/) (2026)
- [Attention Quantization for Tabular Foundation Models](https://mlsanity.com/paper/2609.13031/) (2026)

## Abstract (arXiv)

Quantization is a powerful tool for accelerating large language model (LLM) inference, but the accuracy-performance trade-offs across different formats remain unclear. In this paper, we conduct the most comprehensive empirical study to date, evaluating FP8, INT8, and INT4 quantization across academic benchmarks and real-world tasks on the entire Llama-3.1 model family. Through over 500,000 evaluations, our investigation yields several key findings: (1) FP8 (W8A8-FP) is effectively lossless across all model scales, (2) well-tuned INT8 (W8A8-INT) achieves surprisingly low (1-3%) accuracy degradation, and (3) INT4 weight-only (W4A16-INT) is more competitive than expected, rivaling 8-bit quantization. Further, we investigate the optimal quantization format for different deployments by analyzing inference performance through the popular vLLM framework. Our analysis provides clear deployment recommendations: W4A16 is the most cost-efficient for synchronous setups, while W8A8 dominates in asynchronous continuous batching. For mixed workloads, the optimal choice depends on the specific use case. Our findings offer practical, data-driven guidelines for deploying quantized LLMs at scale -- ensuring the best balance between speed, efficiency, and accuracy.