Very Deep VAEs (ImageNet-64) TPS calculator

Open weights OpenAI 125M 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 · 295 tok/s

Fastest card

B200

27,106 tok/s · 180 GB

Which GPUs can run Very Deep VAEs (ImageNet-64)?

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: OpenAI
Organisation type: Industry
Country: United States of America
Published: 16 March 2021
Authors: Rewon Child

What it does

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

Domain: Image generation
Task: Image generation, Image representation

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: tokens

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 × 10²¹ FLOP
How it was established: 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: 32
Wall-clock time: 420 hours (17.5 days)
Power draw: 19.5 kW

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: Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
Last updated: 11 February 2026

The extremes

The ten fastest GPUs that run Very Deep VAEs (ImageNet-64)

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 Very Deep VAEs (ImageNet-64)

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 you need to run it

Minimum card

Tesla C1080

Memory needed

0.8 GB

Fastest

27,106 tok/s

Very Deep VAEs (ImageNet-64) 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.

The least hardware that works is a Tesla C1080. Its 4 GB is enough at Q8_0 compression, giving roughly 295 tokens per second.

At the other end, a B200 generates roughly 27,106 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Background

Very Deep VAEs (ImageNet-64) was published by OpenAI, in United States of America, in March 2021. The organisation is categorised as industry.

It works in Image generation, and is recorded as doing image generation, Image representation.

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.

Reading the throughput figures

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

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.

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.

What went into building it

Training it took roughly 1.8 × 10²¹ FLOP of computation, on NVIDIA V100 — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for Very Deep VAEs (ImageNet-64)

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

Look at what Very Deep VAEs (ImageNet-64) actually needs — around 0.8 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Very Deep VAEs (ImageNet-64) stops fitting a card that seemed fine.
03

Choose how far you will compress it

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 Very Deep VAEs (ImageNet-64) by squeezing it further than you would want.
04

Sort by speed

Ranking by tokens per second for Very Deep VAEs (ImageNet-64) follows memory bandwidth, not core counts, which is why the B200 tops it at 27,106 tok/s.
05

Check the fit verdict before buying

A tight fit runs Very Deep VAEs (ImageNet-64) 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 Very Deep VAEs (ImageNet-64) alone — a card is usually bought for more than one model.

Answers

Very Deep VAEs (ImageNet-64) — common questions

Is Very Deep VAEs (ImageNet-64) open source?

Its weights are published, so Very Deep VAEs (ImageNet-64) 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 Very Deep VAEs (ImageNet-64) have?

Very Deep VAEs (ImageNet-64) has 125M parameters. 125M. 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 Very Deep VAEs (ImageNet-64)?

Very Deep VAEs (ImageNet-64) was published by OpenAI, based in United States of America, categorised as industry.

When was Very Deep VAEs (ImageNet-64) released?

Very Deep VAEs (ImageNet-64) 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 Very Deep VAEs (ImageNet-64) used for?

Very Deep VAEs (ImageNet-64) works in Image generation, and is recorded as handling image generation, Image representation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Very Deep VAEs (ImageNet-64)?

The weights for Very Deep VAEs (ImageNet-64) 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 Very Deep VAEs (ImageNet-64)?

Around 1.8 × 10²¹ 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 Very Deep VAEs (ImageNet-64) 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 Very Deep VAEs (ImageNet-64) is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run Very Deep VAEs (ImageNet-64) faster?

Two cards buy memory rather than speed. That matters for Very Deep VAEs (ImageNet-64) only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for Very Deep VAEs (ImageNet-64)?

Because capacity varies, so does how hard Very Deep VAEs (ImageNet-64) has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Very Deep VAEs (ImageNet-64) speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 16,264–43,369 tok/s on the B200 rather than a single number.

What GPU do I need to run Very Deep VAEs (ImageNet-64)?

The smallest card in our catalogue that holds Very Deep VAEs (ImageNet-64) 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 Very Deep VAEs (ImageNet-64) 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 Very Deep VAEs (ImageNet-64) clear that.

How much VRAM does Very Deep VAEs (ImageNet-64) 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 Very Deep VAEs (ImageNet-64) 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 Very Deep VAEs (ImageNet-64) 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 Very Deep VAEs (ImageNet-64) 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 Very Deep VAEs (ImageNet-64) 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.

Source

Original publication

Record last updated 11 February 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