SourceScore

Verified claim · AI-ML · 100% confidence

GPTQ introduced in: Frantar et al. 2022 — accurate post-training quantization for GPT models.

Last verified 2026-05-16 · Methodology veritas-v0.1 · a9ab1ec12062f7ae

Structured fields

Subject
GPTQ
Predicate
introduced_in
Object
Frantar et al. 2022 — accurate post-training quantization for GPT models
Confidence
100%
Tags
gptq · quantization · ist-austria · inference · post-training · 2022 · introduced_in

Sources (2)

  1. [1] preprint · arXiv (Frantar, Ashkboos, Hoefler, Alistarh / IST Austria) · 2022-10-31

    GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
    In this paper, we present a new one-shot weight quantization method based on approximate second-order information, that is both highly-accurate and highly-efficient. Specifically, GPTQ can quantize GPT models with 175 billion parameters in approximately four GPU hours, reducing the bitwidth down to 3 or 4 bits per weight, with negligible accuracy degradation relative to the uncompressed baseline.
  2. [2] github release · IST Austria DAS Lab · 2022-10-31

    GPTQ — official IST-DASLab GitHub repository

Cite this claim

Ready-to-paste citation (Markdown / plain text):

GPTQ introduced in: Frantar et al. 2022 — accurate post-training quantization for GPT models. — SourceScore Claim a9ab1ec12062f7ae (verified 2026-05-16). https://sourcescore.org/api/v1/claims/a9ab1ec12062f7ae.json

Embed this claim

Drop this iframe into any blog post, docs page, or knowledge base. The widget renders the signed claim + primary source + click-through to this canonical page. CC-BY 4.0; attribution included.

<iframe src="https://sourcescore.org/embed/claim/a9ab1ec12062f7ae/" width="100%" height="360" frameborder="0" loading="lazy" title="GPTQ introduced in: Frantar et al. 2022 — accurate post-training quantization for GPT models."></iframe>

Preview: open in new tab

Related claims

Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.

Use this claim in your code

Fetch this signed envelope from your application. The response includes the verbatim excerpt, primary source URLs, and an HMAC-SHA256 signature you can verify locally for audit trails.

cURL

curl https://sourcescore.org/api/v1/claims/a9ab1ec12062f7ae.json

JavaScript / TypeScript

const r = await fetch("https://sourcescore.org/api/v1/claims/a9ab1ec12062f7ae.json"); const envelope = await r.json(); console.log(envelope.claim.statement); // "GPTQ introduced in: Frantar et al. 2022 — accurate post-training quantization for GPT models."

Python

import httpx r = httpx.get("https://sourcescore.org/api/v1/claims/a9ab1ec12062f7ae.json") envelope = r.json() print(envelope["claim"]["statement"]) # "GPTQ introduced in: Frantar et al. 2022 — accurate post-training quantization for GPT models."

LangChain (retrieve-then-cite)

from langchain_core.tools import tool import httpx @tool def get_gptq_fact() -> dict: """Fetch the verified SourceScore claim for GPTQ.""" r = httpx.get("https://sourcescore.org/api/v1/claims/a9ab1ec12062f7ae.json") return r.json()