SparseOPT-66B

Closed weights Institute of Science and Technology Austria (ISTA) 66B parameters January 2023

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Institute of Science and Technology Austria (ISTA)
Organisation type
Academia
Country
Austria
Published
2 January 2023
Authors
Elias Frantar, Dan Alistarh

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Language modeling/generation, Question answering
Base model
OPT-66B

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
66B
Training data
tokens

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Open source

code is Apache 2.0 https://github.com/IST-DASLab/sparsegpt

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident
Citations
1,267
Benchmark data
SparseOPT-66B

Sources

Where this record came from and when it was last checked.

Reference
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
Last updated
25 May 2026

What the numbers mean

Where it came from

SparseOPT-66B was published by Institute of Science and Technology Austria (ISTA), in Austria, in January 2023. academia is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Question answering.

It builds on OPT-66B, which is why it shares that model's general shape and size.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Answers

SparseOPT-66B — common questions

01

What GPU do I need to run SparseOPT-66B?

None. SparseOPT-66B is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

02

Is SparseOPT-66B open source?

No. SparseOPT-66B has not had its weights published, so it exists only as a service controlled by its owner.

03

How many parameters does SparseOPT-66B have?

SparseOPT-66B has 66B parameters. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

04

Who created SparseOPT-66B?

SparseOPT-66B was published by Institute of Science and Technology Austria (ISTA), based in Austria, categorised as academia.

05

When was SparseOPT-66B released?

SparseOPT-66B was published in January 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is SparseOPT-66B used for?

SparseOPT-66B works in Language, and is recorded as handling language modeling/generation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Source

Original publication

Record last updated 25 May 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.