SRU++ Base

Closed weights ASAPP 148M parameters February 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
ASAPP
Organisation type
Industry
Country
United States of America
Published
24 February 2021
Authors
Tao Lei

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
148M
Training data
tokens
Epochs
25.56

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
2.6 × 10¹⁹ FLOP

8 V100 GPU days 8*24*60*60*125000000000000*0.3=2.592e+19

How it was established
Hardware

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
NVIDIA V100
Chips used
8
Wall-clock time
24 hours
Power draw
4.9 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

code with MIT license (no script for WT103) https://github.com/asappresearch/sru/blob/master/language_model/README.md

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
54
Benchmark data
SRU++ Base

Sources

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

Reference
When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute
Last updated
1 December 2025

What the numbers mean

About this model

SRU++ Base was published by ASAPP, in United States of America, in February 2021. industry is the category the publisher falls under.

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

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

What went into building it

Producing it required around 2.6 × 10¹⁹ FLOP of arithmetic, on NVIDIA V100, which is a statement about the training budget rather than about inference.

Answers

SRU++ Base — common questions

01

How much compute was used to train SRU++ Base?

Around 2.6 × 10¹⁹ FLOP, on NVIDIA V100. 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 SRU++ Base?

None. SRU++ Base 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 SRU++ Base open source?

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

04

How many parameters does SRU++ Base have?

SRU++ Base has 148M 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.

05

Who created SRU++ Base?

SRU++ Base was published by ASAPP, based in United States of America, categorised as industry.

06

When was SRU++ Base released?

SRU++ Base was published in February 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.

07

What is SRU++ Base used for?

SRU++ Base 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 1 December 2025

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.