MoEFold2D TPS calculator

Open weights George Washington University 960K parameters September 2024

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 · 38,400 tok/s

Fastest card

B200

3,529,412 tok/s · 180 GB

Which GPUs can run MoEFold2D?

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
3,529,412 tok/s 2,117,647–5,647,059 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.7 GB	Q8_0	Comfortable
3,529,412 tok/s 2,117,647–5,647,059 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.7 GB	Q8_0	Comfortable
2,818,324 tok/s 1,690,994–4,509,318 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.7 GB	Q8_0	Comfortable
2,818,324 tok/s 1,690,994–4,509,318 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.7 GB	Q8_0	Comfortable
2,253,971 tok/s 1,352,382–3,606,353 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
2,157,353 tok/s 1,294,412–3,451,765 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.7 GB	Q8_0	Comfortable
2,157,353 tok/s 1,294,412–3,451,765 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.7 GB	Q8_0	Comfortable
2,064,706 tok/s 1,238,824–3,303,529 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.7 GB	Q8_0	Comfortable
1,832,426 tok/s 1,099,456–2,931,882 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
1,832,426 tok/s 1,099,456–2,931,882 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
1,832,426 tok/s 1,099,456–2,931,882 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
1,738,235 tok/s 1,042,941–2,781,176 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
1,482,353 tok/s 889,412–2,371,765 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
1,482,353 tok/s 889,412–2,371,765 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.7 GB	Q8_0	Comfortable
1,482,353 tok/s 889,412–2,371,765 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
1,482,353 tok/s 889,412–2,371,765 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
1,482,353 tok/s 889,412–2,371,765 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
1,128,706 tok/s 677,224–1,805,929 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.7 GB	Q8_0	Comfortable
1,128,706 tok/s 677,224–1,805,929 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.7 GB	Q8_0	Comfortable
940,588 tok/s 564,353–1,504,941 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
920,515 tok/s 552,309–1,472,824 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
900,000 tok/s 540,000–1,440,000 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.7 GB	Q8_0	Comfortable
900,000 tok/s 540,000–1,440,000 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.7 GB	Q8_0	Comfortable
900,000 tok/s 540,000–1,440,000 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.7 GB	Q8_0	Comfortable
900,000 tok/s 540,000–1,440,000 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	0.7 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: George Washington University
Organisation type: Academia
Country: United States of America
Published: 22 September 2024
Authors: Xiangyun Qiu

What it does

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

Domain: Biology
Task: RNA structure 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: 960K
Training data: tokens

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

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: MoEFold2D: Safeguarding RNA Secondary Structure Prediction with a Mixture of Deep Learning and Physics-based Experts
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run MoEFold2D

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 MoEFold2D

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

What it takes to run this model

Minimum card

Tesla C1080

Memory needed

0.7 GB

Fastest

3,529,412 tok/s

MoEFold2D is small enough at 960K parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the Tesla C1080 with 4 GB, running it at Q8_0 and producing around 38,400 tokens per second.

Top of the range is the B200, at roughly 3,529,412 tokens per second thanks to 8,000 GB/s of bandwidth.

Where it came from

MoEFold2D was published by George Washington University, in United States of America, in September 2024. It comes out of academia.

It works in Biology, and is recorded as doing rNA structure prediction.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold.

Understanding the speeds

Across every card that can run it, the middle of the range is about 99,105.9 tokens per second, and 818 of them clear the ten tokens per second that roughly matches reading speed.

It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.

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.

Step by step

How to choose a GPU for MoEFold2D

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

01

Check what it needs before anything else

The table lists every card that can hold MoEFold2D — around 0.7 GB at Q8_0. That figure, not the card's headline performance, is what decides whether it runs.
02

Match the context to your actual use

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason MoEFold2D stops fitting a card that seemed fine.
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 MoEFold2D by squeezing it further than you would want.
04

Sort by speed

Ranking by tokens per second for MoEFold2D follows memory bandwidth, not core counts, which is why the B200 tops it at 3,529,412 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage MoEFold2D from those with room to spare. Buy for the second if the context might grow.
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 MoEFold2D alone — a card is usually bought for more than one model.

Answers

MoEFold2D — common questions

Where can I download MoEFold2D?

The weights for MoEFold2D are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run MoEFold2D 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 MoEFold2D assume it is fully resident.

Would two GPUs run MoEFold2D faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold MoEFold2D on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for MoEFold2D?

A larger card holds a more accurate copy. Across the cards that run MoEFold2D, 1 compression levels are used; the floor control above pins it to one.

How accurate are these MoEFold2D speed estimates?

These are estimates with real error bars. The fastest result here, 2,117,647–5,647,059 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 MoEFold2D?

The smallest card in our catalogue that holds MoEFold2D is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.7 GB, and produces roughly 38,400 tokens per second. 818 cards in total can run it.

How fast is MoEFold2D on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 3,529,412 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 MoEFold2D clear that.

How much VRAM does MoEFold2D need?

About 0.7 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 MoEFold2D on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.7 GB and generating roughly 657,353 tokens per second — a comfortable fit.

Can I run MoEFold2D on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.7 GB and generating roughly 402,529 tokens per second — a comfortable fit.

Can I run MoEFold2D on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.7 GB and generating roughly 498,529 tokens per second — a comfortable fit.

Can I run MoEFold2D on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.7 GB and generating roughly 591,176 tokens per second — a comfortable fit.

Is MoEFold2D open source?

Its weights are published, so MoEFold2D 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 MoEFold2D have?

MoEFold2D has 960K parameters. 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 MoEFold2D?

MoEFold2D was published by George Washington University, based in United States of America, categorised as academia.

When was MoEFold2D released?

MoEFold2D 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.

What is MoEFold2D used for?

MoEFold2D works in Biology, and is recorded as handling rNA structure 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.

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