ChemBERTa TPS calculator

Open weights University of Toronto,Reverie Labs,DeepChem 125M parameters October 2020

Each card below is assessed against this model at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from the card's memory bandwidth and the size of the model once compressed.

Calculated for this model

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 295 tok/s

Fastest card

B200

27,106 tok/s · 180 GB

Which GPUs can run ChemBERTa?

Set the inputs, read the answer

Context length tokens

A longer conversation needs more memory, which can push this model off smaller cards.

Minimum quality

Hides cards that would only fit the model by compressing it below this point.

Search cards

Card memory

Also show cards that cannot run it

818 cards match

Calculating

					Needs	Quantisation	Fit
27,106 tok/s 16,264–43,369 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.8 GB	Q8_0	Comfortable
27,106 tok/s 16,264–43,369 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.8 GB	Q8_0	Comfortable
21,645 tok/s 12,987–34,632 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.8 GB	Q8_0	Comfortable
21,645 tok/s 12,987–34,632 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.8 GB	Q8_0	Comfortable
17,310 tok/s 10,386–27,697 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.8 GB	Q8_0	Comfortable
16,568 tok/s 9,941–26,510 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.8 GB	Q8_0	Comfortable
16,568 tok/s 9,941–26,510 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.8 GB	Q8_0	Comfortable
15,857 tok/s 9,514–25,371 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.8 GB	Q8_0	Comfortable
14,073 tok/s 8,444–22,517 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.8 GB	Q8_0	Comfortable
14,073 tok/s 8,444–22,517 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.8 GB	Q8_0	Comfortable
14,073 tok/s 8,444–22,517 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.8 GB	Q8_0	Comfortable
13,350 tok/s 8,010–21,359 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
11,384 tok/s 6,831–18,215 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
11,384 tok/s 6,831–18,215 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.8 GB	Q8_0	Comfortable
11,384 tok/s 6,831–18,215 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
11,384 tok/s 6,831–18,215 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
11,384 tok/s 6,831–18,215 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
8,668 tok/s 5,201–13,870 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.8 GB	Q8_0	Comfortable
8,668 tok/s 5,201–13,870 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.8 GB	Q8_0	Comfortable
7,224 tok/s 4,334–11,558 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.8 GB	Q8_0	Comfortable
7,070 tok/s 4,242–11,311 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.8 GB	Q8_0	Comfortable
6,912 tok/s 4,147–11,059 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.8 GB	Q8_0	Comfortable
6,912 tok/s 4,147–11,059 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.8 GB	Q8_0	Comfortable
6,912 tok/s 4,147–11,059 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.8 GB	Q8_0	Comfortable
6,912 tok/s 4,147–11,059 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable

Speeds are estimates for a single request — one conversation at a time — calculated from memory bandwidth, model size and quantisation. Real throughput varies with the inference runtime and its version. Figures published by hardware vendors measure many simultaneous requests and are much higher.

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 Toronto,Reverie Labs,DeepChem
Organisation type: Academia,Industry,Industry
Country: Canada, United States of America
Published: 23 October 2020
Authors: Seyone Chithrananda, Gabriel Grand, Bharath Ramsundar

What it does

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

Domain: Biology
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: 125M
Training data: 225,000,000 tokens
Epochs: 3

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: 8.5 × 10¹⁸ FLOP
How it was established: Operation counting,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: 1
Wall-clock time: 48 hours
Power draw: 335 W

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)
Hugging Face: seyonec

How it is classified

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

Record confidence: Likely

Sources

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

Reference: ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run ChemBERTa

Ranked by estimated tokens per second, newest card first where speeds tie. Because generation is bound by memory bandwidth, this ordering follows bandwidth rather than any gaming benchmark.

The smallest GPUs that still run ChemBERTa

The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.

What the numbers mean

The hardware side

Minimum card

Tesla C1080

Memory needed

0.8 GB

Fastest

27,106 tok/s

ChemBERTa is small enough at 125M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

At the low end, a Tesla C1080 handles it — 4 GB, at Q8_0, for about 295 tokens per second.

The quickest result comes from a B200 at around 27,106 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Background

ChemBERTa was published by University of Toronto,Reverie Labs,DeepChem, in Canada, in October 2020. The organisation is categorised as academia,Industry,Industry.

It works in Biology, and is recorded as doing molecular property prediction.

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. It is published under the seyonec organisation on Hugging Face.

Reading the throughput figures

Half the cards that hold it manage more than 761.1 tokens per second, and 818 exceed reading speed outright.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

Training and provenance

The training run consumed about 8.5 × 10¹⁸ FLOP, on NVIDIA V100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Around 225,000,000 tokens went into training it.

Step by step

How to choose a GPU for ChemBERTa

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Read the memory figure first

Every card here has been checked against ChemBERTa — around 0.8 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for ChemBERTa.
03

Set a quality floor

Each card runs the least-compressed copy it can hold — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage ChemBERTa by squeezing it further than you would want.
04

Sort by speed

Sort by speed to see how cards rank for ChemBERTa. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 27,106 tok/s.
05

Check the fit verdict before buying

A tight fit runs ChemBERTa but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

See what else that card runs

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for ChemBERTa alone — a card is usually bought for more than one model.

Answers

ChemBERTa — common questions

What is ChemBERTa used for?

ChemBERTa works in Biology, and is recorded as handling molecular property prediction. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download ChemBERTa?

Its weights are published under the seyonec organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

How much compute was used to train ChemBERTa?

Around 8.5 × 10¹⁸ 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.

Can I run ChemBERTa if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down. Our figures for ChemBERTa assume it is fully resident.

Would two GPUs run ChemBERTa faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold ChemBERTa on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for ChemBERTa?

Because capacity varies, so does how hard ChemBERTa has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these ChemBERTa speed estimates?

These are estimates with real error bars. The fastest result here, 16,264–43,369 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run ChemBERTa?

The smallest card in our catalogue that holds ChemBERTa is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.8 GB, and produces roughly 295 tokens per second. 818 cards in total can run it.

How fast is ChemBERTa on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 27,106 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 818 of the cards that can run ChemBERTa clear that.

How much VRAM does ChemBERTa need?

About 0.8 GB at Q8_0 compression, which is what the smallest card that runs it uses. Less compression needs more: the figures in the memory column above are recalculated for each card, because each one holds the least-compressed version it can.

Can I run ChemBERTa on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.8 GB and generating roughly 5,048 tokens per second — a comfortable fit.

Can I run ChemBERTa on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.8 GB and generating roughly 3,091 tokens per second — a comfortable fit.

Can I run ChemBERTa on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.8 GB and generating roughly 3,829 tokens per second — a comfortable fit.

Can I run ChemBERTa on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.8 GB and generating roughly 4,540 tokens per second — a comfortable fit.

Is ChemBERTa open source?

Its weights are published, so ChemBERTa 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.

How many parameters does ChemBERTa have?

ChemBERTa has 125M parameters. "Our implementation of RoBERTa uses 12 attention heads and 6 layers, resulting in 72 distinct attention mechanisms" -> base model is RoBERTa Base. 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.

Who created ChemBERTa?

ChemBERTa was published by University of Toronto,Reverie Labs,DeepChem, based in Canada, categorised as academia,Industry,Industry.

When was ChemBERTa released?

ChemBERTa was published in October 2020. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

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.

All AI models