cs.LGNov 17, 2026

TempQuant: Learning Adaptive Temperatures for Quantized Language Models

Authors: Mukund Athmaram, Liang Ma, Manoj Rao

Organizations: AMD · Cornell University

Abstract

Large language models are increasingly deployed at low precision, yet quantization can degrade their performance. We study how quantization interacts with decoding settings such as the sampling temperature and top-p by examining how it distorts the model's next-token probabilities. Measuring entropy during generation across deployed temperatures, we find that quantization warms the model on average, and that temperature matters much more for the performance of a quantized model than for its full-precision counterpart. Because quantization and temperature both shape the next-token distribution, we investigate how much the sampling settings can undo what quantization changes, through our method TempQuant, which learns the quantized model's temperature and top-p to bring its next-token probabilities closer to the full-precision model's. We learn these settings at two granularities. The first is a single global setting per requested temperature, which finds nearly the same temperatures that tuning on labeled answers would, without any labels. Model cards typically recommend sampling a quantized model with the same settings as its full-precision counterpart, while we find that different settings can substantially improve its accuracy. On 3-bit Qwen3-4B, for example, global TempQuant raises MATH accuracy from 34% under the configuration recommended for Qwen's quantized releases to 51%. The second sets the temperature and top-p for every token, motivated by our finding that tokens whose rankings flip under quantization tend to need warming, while tokens whose rankings are preserved tend to need cooling. When quantization degrades accuracy substantially, TempQuant recovers much of it, and when degradation is lighter, it still brings the quantized model's behavior closer to the full-precision model's.

Figures & tables

Appendix figures & tables42 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 7, 2026

OnlineQAT: On-Policy Distillation for Ultra-Low-Bit Large Language Models

Quantization-aware training (QAT) can recover much of the accuracy lost when large language models are compressed below four bits. Existing re- covery stages, however, are commonly optimized on fixed completions or teacher-generated answers, whereas the deployed quantized model condi- tions on prefixes generated by itself. Quantization errors can therefore move the model into states that are absent from offline recovery data. We introduce OnlineQAT, a two-stage framework that first obtains a usable low-bit initialization through block-wise QAT and then performs on-policy distillation (OPD) on student-generated responses. At each visited pre- fix, a frozen full-precision teacher provides a sampled reverse-KL training signal. On Qwen3-1.7B, OnlineQAT obtains the best average among the compared quantized methods: 57.28 at W3A16 and 32.52 at W2A16, im- proving over ReasoningQAT by 2.90 and 0.44 points, respectively. The results suggest that student-visited states provide a useful recovery signal beyond fixed-completion training, particularly at three bits.
Oct 21, 2026

Right On Q: Recovering Reasoning under Quantization via Self-Generated Trajectories

Quantization-aware training (QAT) aims to recover reasoning capabilities in low-bit large language models (LLMs). Existing recipes typically supervise the quantized student with the original full-precision model on fixed response sequences. However, the resulting low-bit quantized models still struggle on long-horizon reasoning tasks and often fail to terminate within a token budget that suffices for the full-precision model. We identify two challenges in closing this gap. First, fixed-response supervision leaves a mismatch between training prefixes and those encountered during student generation, and this trajectory divergence grows as responses lengthen. Second, on its own prefixes, the student underpredicts some next-token candidates and overpredicts others, and this distributional misalignment becomes more frequent at high-entropy prefixes. We present OnQ, a low-bit recovery pipeline that combines on-policy distillation and candidate-wise Dynamic KL. Starting from block-wise calibration, the quantized student generates responses and receives full-precision teacher supervision on its own prefixes. Dynamic KL weights forward and reverse KL by each candidate's teacher-student probability ratio to balance correction of under- and overprediction. Across Qwen3-1.7B, 4B, and 8B at 2- and 3-bit precision, OnQ achieves the highest nine-benchmark average, with the largest gains on long-horizon reasoning benchmarks. At 2 bits, it outperforms every baseline on every benchmark at every model size, improving the Qwen3-8B average by 10.26 points over the strongest baseline. It also produces shorter responses with fewer truncations and repetitive errors.
Jun 28, 2026

The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis

Modern LLM deployments often combine quantization with higher sampling temperatures to reduce cost, latency, or repetition, yet safety evaluations usually treat these as fixed implementation details. We test whether models that are safe at FP16 with greedy decoding remain safe after quantization and stochastic sampling, or whether the two factors amplify each other. We evaluate 8 instruction-tuned models from five families across 3 precisions and 6 temperatures, covering 144 configurations on 7 harmfulness benchmarks and generating about 2.0 million responses, which are scored by a six-judge safety ensemble. Contrary to concerns that low-bit deployment erodes alignment, we find that standard quantization is approximately safety-neutral: for 7 of 8 models, AWQ INT4 keeps attack success within about 1.6 percentage points of FP16 or lowers it, with clear degradation only for SmolLM3-3B (34.5% to 44.1%). However, the larger risk comes from sampling: higher temperatures sharply increase decision instability, with DFR reaching 41.9% at T = 1.0, even when average ASR changes only modestly. The two factors do not compound: our Compound Degradation Index remains sub-additive (-0.071 to +0.018), indicating that quantization partially offsets rather than amplifies temperature-induced degradation. Finally, a per-benchmark breakdown shows that single-benchmark evaluation badly understates risk: several models scoring 0% on AdvBench exceed 80% on ManyHarm. Standard INT4/INT8 quantization can therefore be reasonable for well-aligned models, but safety claims should report multi-sample stability across multiple benchmarks rather than rely on a single benchmark at greedy decoding.