Clockwork RNN (CW-RNN)

Closed weights IDSIA,SUPSI 10K parameters February 2014

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
IDSIA,SUPSI
Organisation type
Academia,Academia
Country
Switzerland
Published
14 February 2014
Authors
Jan Koutník, Klaus Greff, Faustino Gomez, Jürgen Schmidhuber

What it does

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

Domain
Speech
Task
Audio classification

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
10K
Training data
tokens

"For every word there are 7 examples from different speakers, which were partitioned into 5 for training and 2 for testing, for a total of 175 sequences (125 train, 50 test)." 25 words × 7 speakers = 175 sequences (125 train / 50 test)

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

Sources

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

Reference
A Clockwork RNN
Last updated
11 February 2026

What the numbers mean

Where it came from

Clockwork RNN (CW-RNN) was published by IDSIA,SUPSI, in Switzerland, in February 2014. The organisation is categorised as academia,Academia.

It works in Speech, and is recorded as doing audio classification.

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

Answers

Clockwork RNN (CW-RNN) — common questions

01

Who created Clockwork RNN (CW-RNN)?

Clockwork RNN (CW-RNN) was published by IDSIA,SUPSI, based in Switzerland, categorised as academia,Academia.

02

When was Clockwork RNN (CW-RNN) released?

Clockwork RNN (CW-RNN) was published in February 2014. 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 Clockwork RNN (CW-RNN) used for?

Clockwork RNN (CW-RNN) works in Speech, and is recorded as handling audio classification. 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.

04

What GPU do I need to run Clockwork RNN (CW-RNN)?

None. Clockwork RNN (CW-RNN) 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 Clockwork RNN (CW-RNN) open source?

No. Clockwork RNN (CW-RNN) has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does Clockwork RNN (CW-RNN) have?

Clockwork RNN (CW-RNN) has 10K parameters. 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 11 February 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.