T-NLRv5 XXL
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
- 3 December 2021
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
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
- 5.4B
- Training data
- tokens
Table 1 of the blogpost
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
- Unreleased
I cannot find repo with model weights or training code though they said: "We will make T-NLRv5 and its capabilities available in the same way as with other Microsoft Turing models. We will leverage its increased capabilities to further improve the execution of popular language tasks in A(opens in new tab)zure Cognitive Services(opens in new tab). Customers will automatically benefit from these. Customers interested in using Turing models for their own specific task can submit a request to join …
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
Highest score at SuperGLUE leaderboard version 2.0 in terms of CB (CommitmentBank-Av. F1/Accuracy; together with Ernie 3.0) and ReCoRD (Reading Comprehsention with Commonsense Reasoning-F1/Accuracy) https://super.gluebenchmark.com/leaderboard/
Sources
Where this record came from and when it was last checked.
- Reference
- Microsoft : Turing-NLRv5 achieves new performance milestones
- Last updated
- 28 November 2025
What the numbers mean
Background
T-NLRv5 XXL was published by Microsoft, in the country recorded as United States of America, during December 2021. The publishing organisation is categorised as industry.
It works in the domain of Language.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
How it was trained
Its inclusion criterion: sOTA improvement.
Answers
T-NLRv5 XXL — common questions
T-NLRv5 XXL— how many parameters does it have?
It has a parameter count of 5.4B. Table 1 of the blogpost. 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.
T-NLRv5 XXL— who created it?
It was published by Microsoft, based in United States of America, an organisation categorised as industry.
T-NLRv5 XXL— when was it released?
It was published in December 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.
T-NLRv5 XXL— what is it used for?
It works in the domain of Language. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
T-NLRv5 XXL— 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.
T-NLRv5 XXL— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
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.