DLRM-2020

Closed weights Facebook AI 100B parameters May 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
Facebook AI
Organisation type
Industry
Country
United States of America
Published
31 May 2019
Authors
Maxim Naumov, Dheevatsa Mudigere, Hao-Jun Michael Shi, Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson G. Azzolini, Dmytro Dzhulgakov, Andrey Mallevich, Ilia Cherniavskii, Yinghai Lu, Raghuraman Krishnamoorthi, Ansha Yu, Volodymyr Kondratenko, Stephanie Pereira, Xianjie Chen, Wenlin Chen, Vijay Rao, Bill Jia, Liang Xiong, Misha Smelyanskiy

What it does

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

Domain
Recommendation
Task
Recommender system
Numerical format
FP32

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
100B

Figure 1 https://arxiv.org/abs/2104.05158

Training data
38,571,428 tokens

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 × 10¹⁸ FLOP

Figure 1 https://arxiv.org/abs/2104.05158

How it was established
Reported

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

MIT, training/inference code: https://github.com/facebookresearch/dlrm

How it is classified

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

Why it is tracked
SOTA improvement

"In this paper, we develop a state-of-the-art deep learning recommendation model (DLRM)"

Record confidence
Confident
Citations
908

Sources

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

Reference
Deep Learning Recommendation Model for Personalization and Recommendation Systems
Last updated
25 May 2026

What the numbers mean

Where it came from

DLRM-2020 was published by Facebook AI, in United States of America, in May 2019. The organisation is categorised as industry.

It works in Recommendation, and is recorded as doing recommender system.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

How it was trained

Producing it required around 4 × 10¹⁸ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

It was trained on about 38,571,428 tokens of text.

Its inclusion criterion is sOTA improvement.

Answers

DLRM-2020 — common questions

01

How many parameters does DLRM-2020 have?

DLRM-2020 has 100B parameters. Figure 1 https://arxiv.org/abs/2104.05158. 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.

02

Who created DLRM-2020?

DLRM-2020 was published by Facebook AI, based in United States of America, categorised as industry.

03

When was DLRM-2020 released?

DLRM-2020 was published in May 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.

04

What is DLRM-2020 used for?

DLRM-2020 works in Recommendation, and is recorded as handling recommender system. 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.

05

How much compute was used to train DLRM-2020?

Around 4 × 10¹⁸ 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.

06

What GPU do I need to run DLRM-2020?

None. DLRM-2020 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.

07

Is DLRM-2020 open source?

No. DLRM-2020 has not had its weights published, so it exists only as a service controlled by its owner.

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.