bRSM + cache

Closed weights Numenta,Incubator 491 2.6M parameters December 2019

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
Numenta,Incubator 491
Organisation type
Industry,Industry
Country
United States of America, Australia
Published
2 December 2019
Authors
Jeremy Gordon, David Rawlinson, Subutai Ahmad

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
2.6M

Table 2

Training data
912,344 tokens

batch size 300 "the bRSM model overfits quickly to the PTB training set, as illustrated by increasing volatility and ultimately a quick rise in test loss after 40-60,000 mini-batches of training." 300*60000 / 912344 = 19.7 epochs

Epochs
19

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
2.8 × 10¹⁴ FLOP

6 FLOP / parameter / token * 2550000 parameters * 300 tokens per batch [speculatively, I am not sure if it is sequences per batch or tokens per batch] * 60000 steps = 2.754e+14 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
Open source

GNU (copyleft) license for code: https://github.com/numenta/nupic.research/tree/master/projects/rsm

How it is classified

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

Record confidence
Speculative
Citations
6
Benchmark data
bRSM + cache

Sources

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

Reference
Long Distance Relationships without Time Travel: Boosting the Performance of a Sparse Predictive Autoencoder in Sequence Modeling
Last updated
25 May 2026

What the numbers mean

Where it came from

bRSM + cache was published by Numenta,Incubator 491, in United States of America, in December 2019. industry,Industry 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.

Training and provenance

Producing it required around 2.8 × 10¹⁴ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

It was trained on about 912,344 tokens of text.

Answers

bRSM + cache — common questions

01

When was bRSM + cache released?

bRSM + cache was published in December 2019. 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 bRSM + cache used for?

bRSM + cache works in Language, and is recorded as handling language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

03

How much compute was used to train bRSM + cache?

Around 2.8 × 10¹⁴ 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 bRSM + cache?

None. bRSM + cache 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 bRSM + cache open source?

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

06

How many parameters does bRSM + cache have?

bRSM + cache has 2.6M parameters. Table 2. 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 bRSM + cache?

bRSM + cache was published by Numenta,Incubator 491, based in United States of America, categorised as industry,Industry.

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.