SPIDER2 TPS calculator

Open weights Griffith University,University of Iowa,Dezhou University 409.5K parameters October 2016

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 · 90,014 tok/s

Fastest card

B200

8,273,352 tok/s · 180 GB

Which GPUs can run SPIDER2?

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
8,273,352 tok/s 4,964,011–13,237,362 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.7 GB	Q8_0	Comfortable
8,273,352 tok/s 4,964,011–13,237,362 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.7 GB	Q8_0	Comfortable
6,606,478 tok/s 3,963,887–10,570,365 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.7 GB	Q8_0	Comfortable
6,606,478 tok/s 3,963,887–10,570,365 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.7 GB	Q8_0	Comfortable
5,283,569 tok/s 3,170,141–8,453,711 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
5,057,086 tok/s 3,034,252–8,091,338 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.7 GB	Q8_0	Comfortable
5,057,086 tok/s 3,034,252–8,091,338 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.7 GB	Q8_0	Comfortable
4,839,911 tok/s 2,903,946–7,743,857 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.7 GB	Q8_0	Comfortable
4,295,421 tok/s 2,577,252–6,872,673 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
4,295,421 tok/s 2,577,252–6,872,673 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
4,295,421 tok/s 2,577,252–6,872,673 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
4,074,626 tok/s 2,444,775–6,519,401 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
3,474,808 tok/s 2,084,885–5,559,692 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
3,474,808 tok/s 2,084,885–5,559,692 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.7 GB	Q8_0	Comfortable
3,474,808 tok/s 2,084,885–5,559,692 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
3,474,808 tok/s 2,084,885–5,559,692 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
3,474,808 tok/s 2,084,885–5,559,692 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
2,645,818 tok/s 1,587,491–4,233,309 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.7 GB	Q8_0	Comfortable
2,645,818 tok/s 1,587,491–4,233,309 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.7 GB	Q8_0	Comfortable
2,204,848 tok/s 1,322,909–3,527,757 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
2,157,794 tok/s 1,294,676–3,452,470 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
2,109,705 tok/s 1,265,823–3,375,527 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.7 GB	Q8_0	Comfortable
2,109,705 tok/s 1,265,823–3,375,527 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.7 GB	Q8_0	Comfortable
2,109,705 tok/s 1,265,823–3,375,527 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.7 GB	Q8_0	Comfortable
2,109,705 tok/s 1,265,823–3,375,527 · 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: Griffith University,University of Iowa,Dezhou University
Organisation type: Academia,Academia,Academia
Country: Australia, United States of America, China
Published: 28 October 2016
Authors: Yuedong Yang, Rhys Heffernan, Kuldip Paliwal, James Lyons, Abdollah Dehzangi, Alok Sharma, Jihua Wang, Abdul Sattar, and Yaoqi Zhou

What it does

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

Domain: Biology
Task: Protein folding prediction, Proteins
Approach: Supervised

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: 409.5K
Training data: 13,893,600 tokens
Epochs: 120

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: 1.8 × 10¹⁶ FLOP
How it was established: Operation counting

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 (non-commercial)

How it is classified

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

Why it is tracked: SOTA improvement
Record confidence: Likely

Sources

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

Reference: SPIDER2: A Package to Predict Secondary Structure, Accessible Surface Area, and Main-Chain Torsional Angles by Deep Neural Networks
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run SPIDER2

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 SPIDER2

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

0.7 GB

Fastest

8,273,352 tok/s

SPIDER2 is small enough at 409.5K 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 90,014 tokens per second.

Top of the range is the B200, at roughly 8,273,352 tokens per second thanks to 8,000 GB/s of bandwidth.

Where it came from

SPIDER2 was published by Griffith University,University of Iowa,Dezhou University, in Australia, in October 2016. It comes out of academia,Academia,Academia.

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

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.

Understanding the speeds

Half the cards that hold it manage more than 232,315.7 tokens per second, and 818 exceed reading speed outright.

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.

Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.

Training and provenance

The training run consumed about 1.8 × 10¹⁶ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The training set ran to roughly 13,893,600 tokens.

The reason it appears in this catalogue at all is sOTA improvement.

Step by step

How to choose a GPU for SPIDER2

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

Every card here has been checked against SPIDER2 — around 0.7 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context SPIDER2 can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Compression is what makes SPIDER2 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

Rank by throughput rather than spec sheet

Ranking by tokens per second for SPIDER2 follows memory bandwidth, not core counts, which is why the B200 tops it at 8,273,352 tok/s.
05

Look at the headroom, not just the fit

Tight means SPIDER2 loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
06

Open the card you have settled on

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for SPIDER2 alone — a card is usually bought for more than one model.

Answers

SPIDER2 — common questions

What is SPIDER2 used for?

SPIDER2 works in Biology, and is recorded as handling protein folding prediction, Proteins. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download SPIDER2?

The weights for SPIDER2 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 SPIDER2?

Around 1.8 × 10¹⁶ FLOP. 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 SPIDER2 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 SPIDER2 assume it is fully resident.

Would two GPUs run SPIDER2 faster?

Two cards buy memory rather than speed. That matters for SPIDER2 only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for SPIDER2?

Each card is shown running the least-compressed copy it can hold, and SPIDER2 appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these SPIDER2 speed estimates?

These are estimates with real error bars. The fastest result here, 4,964,011–13,237,362 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 SPIDER2?

The smallest card in our catalogue that holds SPIDER2 is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.7 GB, and produces roughly 90,014 tokens per second. 818 cards in total can run it.

How fast is SPIDER2 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 8,273,352 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 SPIDER2 clear that.

How much VRAM does SPIDER2 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 SPIDER2 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 1,540,912 tokens per second — a comfortable fit.

Can I run SPIDER2 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 943,576 tokens per second — a comfortable fit.

Can I run SPIDER2 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 1,168,611 tokens per second — a comfortable fit.

Can I run SPIDER2 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 1,385,786 tokens per second — a comfortable fit.

Is SPIDER2 open source?

Its weights are published, so SPIDER2 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 SPIDER2 have?

SPIDER2 has 409.5K parameters. Three networks, each three layers. First takes in 459 inputs and outputs 12, second and third take in 459 + (12*17) = 663 inputs. Network 1: (459 * 150 + 150) + (150 * 150 + 150) + (150 * 150 + 150) + (150 * 12 + 12) = 116,112 Networks 2 and 3: (663 * 150 + 150) + (150 * 150 + 150) + (150 * 150 + 150) + (150 * 12 + 12) = 146,712 Total: 116,112 + (2 * 146,712) = 409,536. 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 SPIDER2?

SPIDER2 was published by Griffith University,University of Iowa,Dezhou University, based in Australia, categorised as academia,Academia,Academia.

When was SPIDER2 released?

SPIDER2 was published in October 2016. 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