MetaLM

Closed weights Microsoft Research June 2022

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 Research
Organisation type
Industry
Country
United States of America
Published
13 June 2022
Authors
Yaru Hao, Haoyu Song, Li Dong, Shaohan Huang, Zewen Chi, Wenhui Wang, Shuming Ma, Furu Wei

What it does

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

Domain
Multimodal, Language, Vision
Task
Language modeling, Visual question answering, Language modeling/generation, Image captioning
Approach
Self-supervised learning

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.

Training data
646,707,200,000 tokens
Batch size
2,097,152

1024 * 2048 - "The maximum input lengths for non-causal and semi-causal models are 512 and 2048, respectively." (Sec. 3.2, p. 9) and "We pretrain METALM for 300k steps with a batch size of 1024"

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 don't see neither code nor weights here https://github.com/microsoft/unilm/tree/master/metalm

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
Why it is tracked
SOTA improvement

Abstract: "Experimental results across various language-only and vision-language benchmarks show that our model outperforms or is competitive with specialized models on finetuning, zero-shot generalization, and few-shot learning." "Table 7 and Table 8 show the zero-shot captioning results on COCO Karpathy test split, NoCaps validation set, and Flickr30k test set. METALM outperforms recent strong methods on three image captioning datasets." Table 12

Record confidence
Speculative
Citations
110

Sources

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

Reference
Language Models are General-Purpose Interfaces
Last updated
25 May 2026

What the numbers mean

Background

MetaLM was published by Microsoft Research, in United States of America, in June 2022. It comes out of industry.

It works in Multimodal, Language, Vision, and is recorded as doing language modeling, Visual question answering, Language modeling/generation, Image captioning.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Training and provenance

It was trained on about 646,707,200,000 tokens of text.

The reason it appears in this catalogue at all is sOTA improvement.

Answers

MetaLM — common questions

01

Is MetaLM open source?

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

02

How many parameters does MetaLM have?

No parameter count has been published for MetaLM, which is why no memory or speed figure appears on this page.

03

Who created MetaLM?

MetaLM was published by Microsoft Research, based in United States of America, categorised as industry.

04

When was MetaLM released?

MetaLM was published in June 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is MetaLM used for?

MetaLM works in Multimodal, Language, Vision, and is recorded as handling language modeling, Visual question answering, Language modeling/generation, Image captioning. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

What GPU do I need to run MetaLM?

None. MetaLM 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.

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.