FvFold TPS calculator

Open weights Jeonbuk National University 9.2M parameters November 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 · 4,003 tok/s

Fastest card

B200

367,895 tok/s · 180 GB

Which GPUs can run FvFold?

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
367,895 tok/s 220,737–588,632 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.7 GB	Q8_0	Comfortable
367,895 tok/s 220,737–588,632 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.7 GB	Q8_0	Comfortable
293,773 tok/s 176,264–470,037 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.7 GB	Q8_0	Comfortable
293,773 tok/s 176,264–470,037 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.7 GB	Q8_0	Comfortable
234,947 tok/s 140,968–375,915 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
224,876 tok/s 134,926–359,801 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.7 GB	Q8_0	Comfortable
224,876 tok/s 134,926–359,801 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.7 GB	Q8_0	Comfortable
215,219 tok/s 129,131–344,350 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.7 GB	Q8_0	Comfortable
191,007 tok/s 114,604–305,610 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
191,007 tok/s 114,604–305,610 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
191,007 tok/s 114,604–305,610 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
181,188 tok/s 108,713–289,901 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
154,516 tok/s 92,710–247,225 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
154,516 tok/s 92,710–247,225 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.7 GB	Q8_0	Comfortable
154,516 tok/s 92,710–247,225 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
154,516 tok/s 92,710–247,225 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
154,516 tok/s 92,710–247,225 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
117,653 tok/s 70,592–188,245 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.7 GB	Q8_0	Comfortable
117,653 tok/s 70,592–188,245 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.7 GB	Q8_0	Comfortable
98,044 tok/s 58,826–156,870 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
95,952 tok/s 57,571–153,523 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
93,813 tok/s 56,288–150,101 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.7 GB	Q8_0	Comfortable
93,813 tok/s 56,288–150,101 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.7 GB	Q8_0	Comfortable
93,813 tok/s 56,288–150,101 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.7 GB	Q8_0	Comfortable
93,813 tok/s 56,288–150,101 · 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: Jeonbuk National University
Organisation type: Academia
Country: Korea (Republic of)
Published: 1 November 2024
Authors: Pasang Sherpa, Kil To Chong, Hilal Tayara

What it does

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

Domain: Biology
Task: Protein folding 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: 9.2M
Training data: tokens

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 PCIe
Chips used: 1
Power draw: 324 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)

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: FvFold: A model to predict antibody Fv structure using protein language model with residual network and Rosetta minimization
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run FvFold

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 FvFold

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

Hardware requirements in practice

Minimum card

Tesla C1080

Memory needed

0.7 GB

Fastest

367,895 tok/s

FvFold is small enough at 9.2M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The entry point is the Tesla C1080: 4 GB of memory, Q8_0 compression, roughly 4,003 tokens per second.

Top of the range is the B200, at roughly 367,895 tokens per second thanks to 8,000 GB/s of bandwidth.

What this model is

FvFold was published by Jeonbuk National University, in Korea (Republic of), in November 2024. The organisation is categorised as academia.

It works in Biology, and is recorded as doing protein folding 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.

What decides the speed

Across every card that can run it, the middle of the range is about 10,330.5 tokens per second, and 818 of them clear the ten tokens per second that roughly matches reading speed.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

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 FvFold

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

01

Start from the memory column

Look at what FvFold actually needs — around 0.7 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context FvFold can slip off a card that handles short questions easily.
03

Set a quality floor

Compression is what makes FvFold fit smaller cards, at some cost in accuracy — Q8_0 on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Compare tokens per second, not specifications

The speed ordering for FvFold is effectively an ordering by memory bandwidth, which is why the B200 tops it at 367,895 tok/s.
05

Look at the headroom, not just the fit

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

Check the card from the other side

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

Answers

FvFold — common questions

What GPU do I need to run FvFold?

The smallest card in our catalogue that holds FvFold is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.7 GB, and produces roughly 4,003 tokens per second. 818 cards in total can run it.

How fast is FvFold on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 367,895 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 FvFold clear that.

How much VRAM does FvFold 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 FvFold 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 68,520 tokens per second — a comfortable fit.

Can I run FvFold 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 41,958 tokens per second — a comfortable fit.

Can I run FvFold 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 51,965 tokens per second — a comfortable fit.

Can I run FvFold 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 61,622 tokens per second — a comfortable fit.

Is FvFold open source?

Its weights are published, so FvFold 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 FvFold have?

FvFold has 9.2M parameters. "In total, the model contains about 9,209,788 trainable 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 FvFold?

FvFold was published by Jeonbuk National University, based in Korea (Republic of), categorised as academia.

When was FvFold released?

FvFold was published in November 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 FvFold used for?

FvFold works in Biology, and is recorded as handling protein folding 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.

Where can I download FvFold?

The weights for FvFold 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 FvFold if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded FvFold is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run FvFold faster?

Two cards buy memory rather than speed. That matters for FvFold only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for FvFold?

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

How accurate are these FvFold speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 220,737–588,632 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

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