SparseOPT-175B

Closed weights Institute of Science and Technology Austria (ISTA),Neural Magic 87.5B 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),Neural Magic
Organisation type
Academia,Industry
Country
Austria, United States of America
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-175B

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
87.5B
Training data
tokens
Epochs
1.67

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
1.6 × 10²³ FLOP
How it was established
Hardware

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA A100 SXM4 80 GB
Chips used
1
Wall-clock time
4 hours

"All pruning experiments are conducted on a single NVIDIA A100 GPU with 80GB of memory. In this setup, SparseGPT can fully sparsify the 175-billion-parameter models in approximately 4 hours."

Power draw
439 W

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 (but OPT, which you'd need to recreate this model, is non-commercial) https://github.com/IST-DASLab/sparsegpt/blob/master/opt.py

How it is classified

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

Likely above 10²³ FLOP
Yes
Record confidence
Confident
Citations
1,267
Benchmark data
SparseOPT-175B

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

What this model is

SparseOPT-175B was published by Institute of Science and Technology Austria (ISTA),Neural Magic, in Austria, in January 2023. academia,Industry is the category the publisher falls under.

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

It is derived from OPT-175B rather than trained from scratch, which is the usual way a specialised model is produced.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

The training run consumed about 1.6 × 10²³ FLOP, on NVIDIA A100 SXM4 80 GB. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Answers

SparseOPT-175B — common questions

01

Who created SparseOPT-175B?

SparseOPT-175B was published by Institute of Science and Technology Austria (ISTA),Neural Magic, based in Austria, categorised as academia,Industry.

02

When was SparseOPT-175B released?

SparseOPT-175B 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.

03

What is SparseOPT-175B used for?

SparseOPT-175B works in Language, and is recorded as handling language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

04

How much compute was used to train SparseOPT-175B?

Around 1.6 × 10²³ FLOP, on NVIDIA A100 SXM4 80 GB. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

05

What GPU do I need to run SparseOPT-175B?

None. SparseOPT-175B 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.

06

Is SparseOPT-175B open source?

No. SparseOPT-175B has not had its weights published, so it exists only as a service controlled by its owner.

07

How many parameters does SparseOPT-175B have?

SparseOPT-175B has 87.5B 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.

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.