RFA-GATE-Gaussian-Stateful Big

Closed weights University of Washington,DeepMind,Allen Institute for AI,Hebrew University of Jerusalem,The University of Hong Kong 242M parameters March 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
University of Washington,DeepMind,Allen Institute for AI,Hebrew University of Jerusalem,The University of Hong Kong
Organisation type
Academia,Industry,Research collective,Academia,Academia
Country
United States of America, United Kingdom of Great Britain and Northern Ireland, Israel, Hong Kong
Published
3 March 2021
Authors
Hao Peng, Nikolaos Pappas, Dani Yogatama, Roy Schwartz, Noah A. Smith, Lingpeng Kong

What it does

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

Domain
Language
Task
Language modeling/generation, 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
242M

242m

Training data
103,000,000 tokens

"All models are trained for up to 150K gradient steps " batch size 64 "All models use a 512 block size during both training and evaluation, i.e., they read as input a segment of 512 consecutive tokens, without access to the context from previous mini-batches." 512*64*150000/103000000 = 47.72

Epochs
47.72
Batch size
32,768

512*64

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
7.1 × 10¹⁸ FLOP

6 FLOP / token / parameter * 242000000 parameters * 512 tokens per sample * 64 samples per batch * 150000 steps = 7.1368704e+18 FLOP

How it was established
Operation counting

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
Google TPU v3
Chips used
16
Wall-clock time
3 hours

7.1368704e+18 FLOP [estimated compute] / (123000000000000 FLOP / s * 16 GPUs * 3600 sec / hour * 0.3 [assumed precision]) = 3.36 hours

Power draw
14.6 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
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
Confident
Citations
430
Benchmark data
RFA-GATE-Gaussian-Stateful Big

Sources

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

Reference
Random Feature Attention
Last updated
25 May 2026

What the numbers mean

What this model is

RFA-GATE-Gaussian-Stateful Big was published by University of Washington,DeepMind,Allen Institute for AI,Hebrew University of Jerusalem,The University of Hong Kong, in United States of America, in March 2021. academia,Industry,Research collective,Academia,Academia is the category the publisher falls under.

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

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

How it was trained

Training it took roughly 7.1 × 10¹⁸ FLOP of computation, on Google TPU v3 — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 103,000,000 tokens.

Answers

RFA-GATE-Gaussian-Stateful Big — common questions

01

Who created RFA-GATE-Gaussian-Stateful Big?

RFA-GATE-Gaussian-Stateful Big was published by University of Washington,DeepMind,Allen Institute for AI,Hebrew University of Jerusalem,The University of Hong Kong, based in United States of America, categorised as academia,Industry,Research collective,Academia,Academia.

02

When was RFA-GATE-Gaussian-Stateful Big released?

RFA-GATE-Gaussian-Stateful Big was published in March 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.

03

What is RFA-GATE-Gaussian-Stateful Big used for?

RFA-GATE-Gaussian-Stateful Big works in Language, and is recorded as handling language modeling/generation, Translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

04

How much compute was used to train RFA-GATE-Gaussian-Stateful Big?

Around 7.1 × 10¹⁸ FLOP, on Google TPU v3. 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.

05

What GPU do I need to run RFA-GATE-Gaussian-Stateful Big?

None. RFA-GATE-Gaussian-Stateful Big 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.

06

Is RFA-GATE-Gaussian-Stateful Big open source?

No. RFA-GATE-Gaussian-Stateful Big has not had its weights published, so it exists only as a service controlled by its owner.

07

How many parameters does RFA-GATE-Gaussian-Stateful Big have?

RFA-GATE-Gaussian-Stateful Big has 242M parameters. 242m. 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.

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.