Turing ULRv5

Closed weights Microsoft 2.2B parameters September 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
Microsoft
Organisation type
Industry
Country
United States of America
Published
28 September 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, Question answering, Translation

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
2.2B

2.2B

Training data
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
2.9 × 10²² FLOP

312000000000000 FLOP / GPU / sec [A100] * 256 GPUs * 336 hours * 3600 sec / hour * 0.3 [assumed utilization] = 2.8983951e+22 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
Chips used
256
Wall-clock time
336 hours (14 days)

"two weeks on 256 NVIDIA A100 GPUs"

Power draw
206.7 kW

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

"Microsoft Turing models are also available for custom application building through our private preview program" "If you are a researcher who would like to work with us in assessing and improving Turing models, Microsoft Turing Academic Program (MS-TAP) allows you to submit a proposal and get access to these models in greater detail."

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
Record confidence
Confident

Sources

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

Reference
Microsoft Turing Universal Language Representation model, T-ULRv5, tops XTREME leaderboard and trains 100x faster
Last updated
28 November 2025

What the numbers mean

About this model

Turing ULRv5 was published by Microsoft, in the country recorded as United States of America, during September 2021. The publishing organisation is categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Question answering, Translation.

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

What went into building it

The training run consumed about 2.9 × 10²² FLOP, on hardware recorded as NVIDIA A100. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Its inclusion criterion: sOTA improvement.

Answers

Turing ULRv5 — common questions

01

Turing ULRv5— how much compute was used to train it?

Training consumed around 2.9 × 10²² FLOP, on hardware recorded as 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.

02

Turing ULRv5— what GPU do I need to run it?

None. This 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.

03

Turing ULRv5— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

04

Turing ULRv5— how many parameters does it have?

It has a parameter count of 2.2B. 2.2B. 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.

05

Turing ULRv5— who created it?

It was published by Microsoft, based in United States of America, an organisation categorised as industry.

06

Turing ULRv5— when was it released?

It was published in September 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.

07

Turing ULRv5— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Question answering, Translation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Source

Original publication

Record last updated 28 November 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.