# IST-DASLab/gptq

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

Repository: https://github.com/IST-DASLab/gptq
Canonical: https://ross.abutalabs.com/products/gptq
Homepage: https://arxiv.org/abs/2210.17323
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-03-27T01:46:02+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1414, "days_push": 890, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2360, forks 207 (observed 2026-08-28T04:06:40.879808+00:00)

## What it is
Reference implementation of GPTQ, a one-shot post-training weight quantization method for large generative transformer models based on approximate second-order information. It quantizes models like OPT, BLOOM, and LLaMA to 2/3/4 bits with minimal accuracy loss and includes CUDA kernels for fast quantized inference.

## Use cases
- quantize a large language model to 4-bit or 3-bit weights
- run a 175B-parameter model on a single GPU
- compress OPT or BLOOM models with weight grouping
- evaluate perplexity of quantized language models
- benchmark quantized matrix-vector product CUDA kernels
- apply act-order and true-sequential quantization to LLaMA

## When to choose
- you need research-grade GPTQ quantization of OPT, BLOOM, or LLaMA models
- you want to reproduce the ICLR 2023 GPTQ paper results
- you need fast 3-bit CUDA kernels for generative inference

## When to avoid
- you need a maintained production quantization library with broad model support
- you want easy integration with modern inference frameworks
- you need quantization of non-transformer architectures

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, machine-learning, benchmarking, gpu-computing
- domain: large-language-models, deep-learning, machine-learning, gpu-computing
- platform: python, cli
- tags: quantization, post-training-quantization, model-compression, transformers, cuda-kernels, research-code, iclr-2023, gpu, linux

## Member repositories
- IST-DASLab/gptq (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:40.879808+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:36:07.524258+00:00, confidence not recorded.
  - readme: https://github.com/IST-DASLab/gptq (fetched 2026-08-28T04:06:40.879808+00:00, sha 82c8bcc1264b)
  - homepage: https://arxiv.org/abs/2210.17323 (fetched 2026-08-29T10:16:43.736316+00:00, sha a5080018a865)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T10:16:43.745602+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T10:16:43.753134+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T10:16:43.755046+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T10:16:43.750637+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.