ResNet-RS TPS calculator

Open weights Google Brain,University of California (UC) Berkeley 192M parameters March 2021

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 · 192 tok/s

Fastest card

B200

17,647 tok/s · 180 GB

Which GPUs can run ResNet-RS?

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
17,647 tok/s 10,588–28,235 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.9 GB	Q8_0	Comfortable
17,647 tok/s 10,588–28,235 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.9 GB	Q8_0	Comfortable
14,092 tok/s 8,455–22,547 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.9 GB	Q8_0	Comfortable
14,092 tok/s 8,455–22,547 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.9 GB	Q8_0	Comfortable
11,270 tok/s 6,762–18,032 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
10,787 tok/s 6,472–17,259 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.9 GB	Q8_0	Comfortable
10,787 tok/s 6,472–17,259 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.9 GB	Q8_0	Comfortable
10,324 tok/s 6,194–16,518 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.9 GB	Q8_0	Comfortable
9,162 tok/s 5,497–14,659 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
9,162 tok/s 5,497–14,659 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
9,162 tok/s 5,497–14,659 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
8,691 tok/s 5,215–13,906 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
7,412 tok/s 4,447–11,859 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
7,412 tok/s 4,447–11,859 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.9 GB	Q8_0	Comfortable
7,412 tok/s 4,447–11,859 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
7,412 tok/s 4,447–11,859 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
7,412 tok/s 4,447–11,859 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
5,644 tok/s 3,386–9,030 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.9 GB	Q8_0	Comfortable
5,644 tok/s 3,386–9,030 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.9 GB	Q8_0	Comfortable
4,703 tok/s 2,822–7,525 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
4,603 tok/s 2,762–7,364 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
4,500 tok/s 2,700–7,200 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.9 GB	Q8_0	Comfortable
4,500 tok/s 2,700–7,200 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.9 GB	Q8_0	Comfortable
4,500 tok/s 2,700–7,200 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.9 GB	Q8_0	Comfortable
4,500 tok/s 2,700–7,200 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	0.9 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: Google Brain,University of California (UC) Berkeley
Organisation type: Industry,Academia
Country: United States of America
Published: 13 March 2021
Authors: Irwan Bello, William Fedus, Xianzhi Du, Ekin D. Cubuk, Aravind Srinivas, Tsung-Yi Lin, Jonathon Shlens, Barret Zoph

What it does

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

Domain: Vision
Task: Image classification

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: 192M
Training data: tokens
Epochs: 350

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 × 10²² FLOP
How it was established: Operation counting

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: Google TPU v3

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: Unreleased

How it is classified

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

Record confidence: Confident
Citations: 358

Sources

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

Reference: Revisiting ResNets: Improved Training and Scaling Strategies
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run ResNet-RS

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 ResNet-RS

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

0.9 GB

Fastest

17,647 tok/s

ResNet-RS is small enough at 192M 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 192 tokens per second.

At the other end, a B200 generates roughly 17,647 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Where it came from

ResNet-RS was published by Google Brain,University of California (UC) Berkeley, in United States of America, in March 2021. industry,Academia is the category the publisher falls under.

It works in Vision, and is recorded as doing image classification.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

Understanding the speeds

Across every card that can run it, the middle of the range is about 495.5 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.

How it was trained

Training it took roughly 1.8 × 10²² FLOP of computation, on Google TPU v3 — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for ResNet-RS

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

The table lists every card that can hold ResNet-RS — around 0.9 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

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

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of ResNet-RS — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for ResNet-RS. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 17,647 tok/s.
05

Check the fit verdict before buying

Tight means ResNet-RS 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

See what else that card runs

Following a card through to its own page shows every other model it can hold, which is the question that follows once ResNet-RS is settled.

Answers

ResNet-RS — common questions

How many parameters does ResNet-RS have?

ResNet-RS has 192M parameters. Table 7 appendix B. 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 ResNet-RS?

ResNet-RS was published by Google Brain,University of California (UC) Berkeley, based in United States of America, categorised as industry,Academia.

When was ResNet-RS released?

ResNet-RS was published in March 2021. 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 ResNet-RS used for?

ResNet-RS works in Vision, and is recorded as handling image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download ResNet-RS?

The weights for ResNet-RS 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 ResNet-RS?

Around 1.8 × 10²² FLOP, on Google TPU v3. 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 ResNet-RS 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 ResNet-RS assume it is fully resident.

Would two GPUs run ResNet-RS faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run ResNet-RS alone, the case for pairing is weak.

Why does the quantisation differ between cards for ResNet-RS?

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

How accurate are these ResNet-RS speed estimates?

These are estimates with real error bars. The fastest result here, 10,588–28,235 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 ResNet-RS?

The smallest card in our catalogue that holds ResNet-RS is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.9 GB, and produces roughly 192 tokens per second. 818 cards in total can run it.

How fast is ResNet-RS on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 17,647 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 ResNet-RS clear that.

How much VRAM does ResNet-RS need?

About 0.9 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 ResNet-RS on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.9 GB and generating roughly 3,287 tokens per second — a comfortable fit.

Can I run ResNet-RS on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.9 GB and generating roughly 2,013 tokens per second — a comfortable fit.

Can I run ResNet-RS on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.9 GB and generating roughly 2,493 tokens per second — a comfortable fit.

Can I run ResNet-RS on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.9 GB and generating roughly 2,956 tokens per second — a comfortable fit.

Is ResNet-RS open source?

Its weights are published, so ResNet-RS 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.

Source

Original publication

Record last updated 25 May 2026

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