RetNet

Closed weights Microsoft Research,Tsinghua University 6.7B parameters July 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
Microsoft Research,Tsinghua University
Organisation type
Industry,Academia
Country
United States of America, China
Published
17 July 2023
Authors
Yutao Sun, Li Dong, Shaohan Huang, Shuming Ma, Yuqing Xia, Jilong Xue, Jianyong Wang, Furu Wei

What it does

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

Domain
Language
Task
Language modeling

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
6.7B

Table 2 They later mention testing the memory and throughput of a 13B-parameter model, but it doesn't sound like they trained it long enough to test its perplexity.

Training data
100,000,000,000 tokens
Batch size
4,000,000

4M

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
4 × 10²¹ FLOP

C = 6ND = 6 * 6.7 billion * 100 billion "We train the models with 512 AMD MI200 GPUs." Another rough method: Table 4 shows throughput is 8642.2 words per second during training on an 8xA100 setup, with batch size of 8192. This suggests 2543.1 hours to go through the full 100B tokens ~= 75B words. (8 * 3.12e14) * (2543.1 * 3600) * (0.3) = 6.9e21 FLOPs (low confidence in this as actual training setup used different hardware and much larger batch size, but same OOM is encouraging)

How it was established
Operation counting

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

MIT for code looks like model code not train code: https://github.com/microsoft/unilm/tree/master/retnet

How it is classified

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

Record confidence
Confident
Citations
646

Sources

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

Reference
Retentive Network: A Successor to Transformer for Large Language Models
Last updated
25 May 2026

What the numbers mean

Where it came from

RetNet was published by Microsoft Research,Tsinghua University, in United States of America, in July 2023. industry,Academia is the category the publisher falls under.

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

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

How it was trained

Producing it required around 4 × 10²¹ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

The training set ran to roughly 100,000,000,000 tokens.

Answers

RetNet — common questions

01

When was RetNet released?

RetNet was published in July 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.

02

What is RetNet used for?

RetNet works in Language, and is recorded as handling language modeling. 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.

03

How much compute was used to train RetNet?

Around 4 × 10²¹ FLOP. 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 RetNet?

None. RetNet 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 RetNet open source?

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

06

How many parameters does RetNet have?

RetNet has 6.7B parameters. Table 2 They later mention testing the memory and throughput of a 13B-parameter model, but it doesn't sound like they trained it long enough to test its perplexity. 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 RetNet?

RetNet was published by Microsoft Research,Tsinghua University, based in United States of America, categorised as industry,Academia.

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.