PLUG

Closed weights Alibaba 27B parameters April 2021

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
Alibaba
Organisation type
Industry
Country
China
Published
19 April 2021

What it does

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

Domain
Language
Task
Language modeling/generation

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
27B
Training data
60,000,000,000 tokens

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
3.6 × 10²² FLOP

128 Nvidia A100 for 35 days

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
Chips used
128
Wall-clock time
840 hours (35 days)

35 days

Power draw
103.7 kW
Compute cost
$108,673

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
Hosted access (no API)
Training code
Unreleased

https://nlp.aliyun.com/portal#/BigText_chinese

How it is classified

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

Why it is tracked
SOTA improvement

Was a SOTA in CLUE 1.0 https://www.cluebenchmarks.com/classification10.html

Record confidence
Confident

Sources

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

Last updated
18 December 2025

What the numbers mean

Background

PLUG was published by Alibaba, in China, in April 2021. industry is the category the publisher falls under.

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

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 3.6 × 10²² FLOP, on NVIDIA A100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

It was trained on about 60,000,000,000 tokens of text.

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

PLUG — common questions

01

When was PLUG released?

PLUG was published in April 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

What is PLUG used for?

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

03

How much compute was used to train PLUG?

Around 3.6 × 10²² FLOP, on NVIDIA A100. 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.

04

What GPU do I need to run PLUG?

None. PLUG 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.

05

Is PLUG open source?

No. PLUG has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does PLUG have?

PLUG has 27B 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.

07

Who created PLUG?

PLUG was published by Alibaba, based in China, categorised as industry.

Source

Original publication

Record last updated 18 December 2025

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.