Tensorized Transformer (257M)

Closed weights Tianjin University,Microsoft Research Asia,Beijing Institute of Technology 257M parameters June 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
Tianjin University,Microsoft Research Asia,Beijing Institute of Technology
Organisation type
Academia,Industry,Academia
Country
China
Published
24 June 2019
Authors
Xindian Ma, Peng Zhang, Shuai Zhang, Nan Duan, Yuexian Hou, Ming Zhou, Dawei Song

What it does

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

Domain
Language
Task
Language modeling/generation

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
257M

257M (Table 5)

Training data
103,000,000 tokens
Epochs
30

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
4.8 × 10¹⁸ FLOP

6 FLOP / parameter / token * 257000000 parameters * 103000000 tokens * 30 epochs = 4.76478e+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
NVIDIA P40
Chips used
2
Power draw
1.0 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
Open (non-commercial)

code, no license: https://github.com/szhangtju/The-compression-of-Transformer

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
194
Benchmark data
Tensorized Transformer (257M)

Sources

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

Reference
A Tensorized Transformer for Language Modeling
Last updated
25 May 2026

What the numbers mean

Background

Tensorized Transformer (257M) was published by Tianjin University,Microsoft Research Asia,Beijing Institute of Technology, in the country recorded as China, during June 2019. The publishing organisation is categorised as academia,Industry,Academia.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation.

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

What went into building it

The training run consumed about 4.8 × 10¹⁸ FLOP, on hardware recorded as NVIDIA P40. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Training consumed a corpus of around 103,000,000 tokens of text.

Answers

Tensorized Transformer (257M) — common questions

01

Tensorized Transformer (257M)— how much compute was used to train it?

Training consumed around 4.8 × 10¹⁸ FLOP, on hardware recorded as NVIDIA P40. 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

Tensorized Transformer (257M)— what GPU do I need to run it?

None. This 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

Tensorized Transformer (257M)— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

04

Tensorized Transformer (257M)— how many parameters does it have?

It has a parameter count of 257M. 257M (Table 5). 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

Tensorized Transformer (257M)— who created it?

It was published by Tianjin University,Microsoft Research Asia,Beijing Institute of Technology, based in China, an organisation categorised as academia,Industry,Academia.

06

Tensorized Transformer (257M)— when was it released?

It was published in June 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.

07

Tensorized Transformer (257M)— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

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.