OpenResearchAlpha

ACM Computing Surveys · 17 Nov 2026

Mixed-Precision Quantization for Language Models: Techniques and Prospects

Mariam Rakkah-index 3, Marios Fournarakis, Olga Krestinskaya, Jinane Bazzi, Khaled Salama, Fadi Kurdahi, Ahmed Eltawil, Mohammed Foudah-index 18

1
Citations
Crossref's count; others 0
0
Citations in 2026
so far
18
Leading author's h-index
Mohammed Fouda, in QAI's scholar index
31
References
works it cites, from open citation data

Citations by database

Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.

  • Crossref1
  • OpenCitations0

Citations per year

The current year is still counting.

  • 2026 so far0

Abstract

The rapid scaling of Language Models (LMs) has resulted in unprecedented computational, memory, and energy requirements, making their training and deployment increasingly unsustainable. Quantization has emerged as a crucial compression technique for reducing model size, alleviating memory bottlenecks, and accelerating inference. However, while uniform low-bit quantization (e.g., INT8, INT4) provides significant efficiency gains, it can degrade accuracy in sensitive components of transformer-based LMs. Mixed-precision quantization offers a promising alternative by selectively allocating precision across layers or within tensors to strike a balance between efficiency and accuracy. This survey provides a comprehensive overview of Mixed-Precision quantization frameworks for LMs (MXPLMs). We first review quantization fundamentals, including uniform and non-uniform quantizers, quantization granularity, and methods widely used in post-training quantization. We then categorize and compare recent MXPLM frameworks according to their bit allocation strategies and precision configurations across weights, activations, and key-value caches. A comparative analysis highlights differences in perplexity, zero-shot task performance, and deployment trade-offs. Furthermore, we contrast MXPLMs with earlier mixed-precision quantization methods for deep neural networks, identifying strategies that transfer and those that face challenges in the LM setting. Then, we discuss quantization-compatible hardware, KV cache and mixture-of-experts quantization, and summarize open issues and future directions, including hardware-aware design, activation quantization, and scalable optimization methods for billion-parameter models.

What the data shows

  • Crossref counts 1 citations, the most of the databases. The others count 0.
  • Mohammed Fouda has the highest h-index among the authors (18).

Graph

This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.

Citing paper shares an authorAuthor without a profileSize shows citations, or h-index for authors

Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.

Start with

Authors (8)

Each author's standing in QAI's scholar index: the works their ORCID iD is attached to, and for anyone whose ORCID record names a lab OpenResearch follows, their arXiv preprints matched by name and a shared co-author. Names are as printed on the paper.

ProfileMost-cited paper

Cited by 0 papers

Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.

0 shown
No citing papers for this filter.

References (31)

What it cites, from open citation data, with Crossref's record of each.

Sign in to see 11 more references

A free account opens the rest of the citing papers and references on every paper’s page.