MolPhenix

Closed weights Valence Labs,University of British Columbia (UBC),Vector Institute,University of Toronto,University of Montreal / Université de Montréal,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms) 38.7M parameters September 2024

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
Valence Labs,University of British Columbia (UBC),Vector Institute,University of Toronto,University of Montreal / Université de Montréal,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms)
Organisation type
Industry,Academia,Academia,Academia,Academia,Academia
Country
Canada
Published
10 September 2024
Authors
Philip Fradkin, Puria Azadi, Karush Suri, Frederik Wenkel, Ali Bashashati, Maciej Sypetkowski, Dominique Beaini

What it does

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

Domain
Biology
Task
Cell Biology

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
38.7M

Taken from table 7, "model size" row; "medium (38.7M)"

Training data
tokens

2,150,000 datapoints Based on: - 1,316,283 molecule-concentration pairs - >2,150,000 phenomic experiments Final count = 2,150,000 unique datapoints (2.15e6)

Epochs
100

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
4.3 × 10¹⁸ FLOP

"We utilized an NVIDIA A100 GPU to train Molphenix using Phenom1 and MolGPS embeddings, which takes approximately ∼4.75 hours each." Assume FP16 precision, 40% utilization. 9.5*60*60*312000000000000*0.4=4.26816e+18

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 A100
Chips used
1
Wall-clock time
10 hours

"We utilized an NVIDIA A100 GPU to train Molphenix using Phenom1 and MolGPS embeddings, which takes approximately ∼4.75 hours each."

Power draw
433 W

How it is classified

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

Record confidence
Confident

Sources

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

Reference
How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval
Last updated
28 November 2025

What the numbers mean

About this model

MolPhenix was published by Valence Labs,University of British Columbia (UBC),Vector Institute,University of Toronto,University of Montreal / Université de Montréal,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms), in the country recorded as Canada, during September 2024. It comes out of an organisation categorised as industry,Academia,Academia,Academia,Academia,Academia.

It works in the domain of Biology, and is recorded as performing the task of cell Biology.

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

Training and provenance

The training run consumed about 4.3 × 10¹⁸ FLOP, on hardware recorded as NVIDIA A100. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Answers

MolPhenix — common questions

01

MolPhenix— how much compute was used to train it?

Training consumed around 4.3 × 10¹⁸ FLOP, on hardware recorded as NVIDIA A100. 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

MolPhenix— 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

MolPhenix— 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.

04

MolPhenix— how many parameters does it have?

It has a parameter count of 38.7M. Taken from table 7, "model size" row; "medium (38.7M)". 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

MolPhenix— who created it?

It was published by Valence Labs,University of British Columbia (UBC),Vector Institute,University of Toronto,University of Montreal / Université de Montréal,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms), based in Canada, an organisation categorised as industry,Academia,Academia,Academia,Academia,Academia.

06

MolPhenix— when was it released?

It was published in September 2024. 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

MolPhenix— what is it used for?

It works in the domain of Biology, and is recorded as handling the task of cell Biology. 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.

Source

Original publication

Record last updated 28 November 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.