MoLeR
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
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
- Microsoft Research,Novartis
- Organisation type
- Industry,Industry
- Country
- United States of America, Switzerland
- Published
- 12 May 2024
- Authors
- Krzysztof Maziarz, Henry Jackson-Flux, Pashmina Cameron, Finton Sirockin, Nadine Schneider, Nikolaus Stiefl, Marwin Segler, Marc Brockschmidt
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Drug discovery
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.
- Training data
- 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
- 2.1 × 10¹⁸ FLOP
- How it was established
- Hardware
training speed 95.2 molecules/sec (Table 1) 1.5*10^6 molecules / 95.2 = 15756 seconds = 4 hours (1 epoch) "a few GPU days" - let's assume (!) it was 10 GPU-days 10*24*3600*8126000000000*0.3 = 2.1062592e+18
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 Tesla K80
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
- Open — downloadable
- Model access
- Open weights (unrestricted)
- Training code
- Open source
https://github.com/microsoft/molecule-generation
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Speculative
Sources
Where this record came from and when it was last checked.
- Reference
- Learning to Extend Molecular Scaffolds with Structural Motifs
- Last updated
- 28 November 2025
What the numbers mean
Background
MoLeR was published by Microsoft Research,Novartis, in United States of America, in May 2024. industry,Industry is the category the publisher falls under.
It works in Biology, and is recorded as doing drug discovery.
Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.
Training and provenance
Producing it required around 2.1 × 10¹⁸ FLOP of arithmetic, on NVIDIA Tesla K80, which is a statement about the training budget rather than about inference.
Answers
MoLeR — common questions
How many parameters does MoLeR have?
No parameter count has been published for MoLeR, which is why no memory or speed figure appears on this page.
Who created MoLeR?
MoLeR was published by Microsoft Research,Novartis, based in United States of America, categorised as industry,Industry.
When was MoLeR released?
MoLeR was published in May 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.
What is MoLeR used for?
MoLeR works in Biology, and is recorded as handling drug discovery. These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download MoLeR?
The weights for MoLeR are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
How much compute was used to train MoLeR?
Around 2.1 × 10¹⁸ FLOP, on NVIDIA Tesla K80. 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.
What GPU do I need to run MoLeR?
We cannot say. MoLeR has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
Is MoLeR open source?
Its weights are published, so MoLeR can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
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.