MEGNet (crystal band gap model)

Closed weights University of California San Diego 26.1K parameters April 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
University of California San Diego
Organisation type
Academia
Country
United States of America
Published
10 April 2019
Authors
Chi Chen, Weike Ye, Yunxing Zuo, Chen Zheng, Shyue Ping Ong

What it does

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

Domain
Materials science
Task
Molecular property prediction

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
26.1K

Calculations here: https://docs.google.com/document/d/1BTmyZ9KVTIwkp9z9tRRFsWM5A0QcXiufXrIhujffyso/edit?tab=t.0#heading=h.913mrln2g0cv

Training data
36,720 tokens
Epochs
1,000

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
4.5 × 10¹⁷ FLOP

Calculations here: https://docs.google.com/document/d/1BTmyZ9KVTIwkp9z9tRRFsWM5A0QcXiufXrIhujffyso/edit?tab=t.0#heading=h.lk6l1te7vrkv Updated calculation assuming 100s per epoch and a single GPU. 1000*100*11340000000000*0.4=453600000000000000

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 GeForce GTX 1080 Ti
Chips used
1
Wall-clock time
28 hours
Power draw
283 W

How it is classified

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

Record confidence
Likely
Citations
1,301

Sources

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

Reference
Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
Last updated
25 May 2026

What the numbers mean

What this model is

MEGNet (crystal band gap model) was published by University of California San Diego, in the country recorded as United States of America, during April 2019. The publishing organisation is categorised as academia.

It works in the domain of Materials science, and is recorded as performing the task of molecular property prediction.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

Training it took a computation budget of roughly 4.5 × 10¹⁷ FLOP, on hardware recorded as NVIDIA GeForce GTX 1080 Ti. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 36,720 tokens of text.

Answers

MEGNet (crystal band gap model) — common questions

01

MEGNet (crystal band gap model)— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

02

MEGNet (crystal band gap model)— how many parameters does it have?

It has a parameter count of 26.1K. Calculations here: https://docs.google.com/document/d/1BTmyZ9KVTIwkp9z9tRRFsWM5A0QcXiufXrIhujffyso/edit?tab=t.0#heading=h.913mrln2g0cv. 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.

03

MEGNet (crystal band gap model)— who created it?

It was published by University of California San Diego, based in United States of America, an organisation categorised as academia.

04

MEGNet (crystal band gap model)— when was it released?

It was published in April 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.

05

MEGNet (crystal band gap model)— what is it used for?

It works in the domain of Materials science, and is recorded as handling the task of molecular property prediction. 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.

06

MEGNet (crystal band gap model)— how much compute was used to train it?

Training consumed around 4.5 × 10¹⁷ FLOP, on hardware recorded as NVIDIA GeForce GTX 1080 Ti. 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.

07

MEGNet (crystal band gap model)— 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.

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.