rTop-k(distributed setting)

Closed weights Stanford University 69M parameters May 2020

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
Stanford University
Organisation type
Academia
Country
United States of America
Published
21 May 2020
Authors
Leighton Pate Barnes, Huseyin A. Inan, Berivan Isik, Ayfer Ozgur

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
69M

We adopted a 2-layer LSTM language model architec- ture with 1500 hidden units per layer Okay, let's break this down: - You have a 2-layer LSTM model - Each LSTM layer has 1500 hidden units - The vocabulary size is 10k For each LSTM layer: - There are 4 weight matrices (input, forget, output, cell state) per layer - Each weight matrix has dimensions (input size x 1500 hidden units) - Plus 1500 bias terms per matrix Layer 1: - Input size is 10k (vocab size) - Weight matrices: 4 * (10k * 150…

Training data
912,344 tokens
Epochs
38

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
1.4 × 10¹⁶ FLOP

6 FLOP / token / parameter * 69000000 parameters * 912344 tokens * 38 epochs = 1.4352996e+16 FLOP

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

How it is classified

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

Record confidence
Likely
Citations
71
Benchmark data
rTop-k(distributed setting)

Sources

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

Reference
rTop-k: A Statistical Estimation Approach to Distributed SGD
Last updated
25 May 2026

What the numbers mean

About this model

rTop-k(distributed setting) was published by Stanford University, in United States of America, in May 2020. The organisation is categorised as academia.

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

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

What went into building it

The training run consumed about 1.4 × 10¹⁶ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Around 912,344 tokens went into training it.

Answers

rTop-k(distributed setting) — common questions

01

How much compute was used to train rTop-k(distributed setting)?

Around 1.4 × 10¹⁶ 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.

02

What GPU do I need to run rTop-k(distributed setting)?

None. rTop-k(distributed setting) 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

Is rTop-k(distributed setting) open source?

No. rTop-k(distributed setting) has not had its weights published, so it exists only as a service controlled by its owner.

04

How many parameters does rTop-k(distributed setting) have?

rTop-k(distributed setting) has 69M parameters. We adopted a 2-layer LSTM language model architec- ture with 1500 hidden units per layer Okay, let's break this down: - You have a 2-layer LSTM model - Each LSTM layer has 1500 hidden units - The vocabulary size is 10k For each LSTM layer: - There are 4 weight matrices (input, forget, output, cell state) per layer - Each weight matrix has dimensions (input size x 1500 hidden units) - Plus 1500 bias terms per matrix Layer 1: - Input size is 10k (vocab size) - Weight matrices: 4 * (10k * 1500) = 60 million parameters - Biases: 4 * 1500 = 6000 parameters Layer 2: - Input size is 1500 (output of layer 1) - Weight matrices: 4 * (1500 * 1500) = 9 million parameters - Biases: 4 * 1500 = 6000 parameters Total parameters = 60 million + 6000 + 9 million + 6000 = 69,012,000 So the total number of parameters in this 2-layer 1500-unit LSTM with 10k vocab size is approximately 69 million. 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

Who created rTop-k(distributed setting)?

rTop-k(distributed setting) was published by Stanford University, based in United States of America, categorised as academia.

06

When was rTop-k(distributed setting) released?

rTop-k(distributed setting) was published in May 2020. 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

What is rTop-k(distributed setting) used for?

rTop-k(distributed setting) works in Language, and is recorded as handling language modeling. These are the areas it was designed around; they describe intent rather than a hard boundary.

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.