CogView TPS calculator

Open weights Tsinghua University,Alibaba DAMO Academy 4B parameters May 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 · Q5_K_M · 16.5 tok/s

Fastest card

B200

847 tok/s · 180 GB

Which GPUs can run CogView?

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
847 tok/s 508–1,355 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	5.0 GB	Q8_0	Comfortable
847 tok/s 508–1,355 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	5.0 GB	Q8_0	Comfortable
676 tok/s 406–1,082 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	5.0 GB	Q8_0	Comfortable
676 tok/s 406–1,082 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	5.0 GB	Q8_0	Comfortable
541 tok/s 325–866 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	5.0 GB	Q8_0	Comfortable
518 tok/s 311–828 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	5.0 GB	Q8_0	Comfortable
518 tok/s 311–828 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	5.0 GB	Q8_0	Comfortable
496 tok/s 297–793 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	5.0 GB	Q8_0	Comfortable
440 tok/s 264–704 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	5.0 GB	Q8_0	Comfortable
440 tok/s 264–704 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	5.0 GB	Q8_0	Comfortable
440 tok/s 264–704 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	5.0 GB	Q8_0	Comfortable
417 tok/s 250–667 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	5.0 GB	Q8_0	Comfortable
356 tok/s 213–569 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	5.0 GB	Q8_0	Comfortable
356 tok/s 213–569 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	5.0 GB	Q8_0	Comfortable
356 tok/s 213–569 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	5.0 GB	Q8_0	Comfortable
356 tok/s 213–569 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	5.0 GB	Q8_0	Comfortable
356 tok/s 213–569 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	5.0 GB	Q8_0	Comfortable
271 tok/s 163–433 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	5.0 GB	Q8_0	Comfortable
271 tok/s 163–433 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	5.0 GB	Q8_0	Comfortable
226 tok/s 135–361 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	5.0 GB	Q8_0	Comfortable
221 tok/s 133–353 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	5.0 GB	Q8_0	Comfortable
216 tok/s 130–346 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	5.0 GB	Q8_0	Comfortable
216 tok/s 130–346 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	5.0 GB	Q8_0	Comfortable
216 tok/s 130–346 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	5.0 GB	Q8_0	Comfortable
216 tok/s 130–346 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	5.0 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: Tsinghua University,Alibaba DAMO Academy
Organisation type: Academia,Industry
Country: China
Published: 26 May 2021
Authors: Ming Ding, Zhuoyi Yang, Wenyi Hong, Wendi Zheng, Chang Zhou, Da Yin, Junyang Lin, Xu Zou, Zhou Shao, Hongxia Yang, Jie Tang

What it does

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

Domain: Image generation
Task: Text-to-image, Image generation
Approach: Self-supervised learning
Numerical format: FP16

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: 4B
Training data: 964,800,000,000 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: 2.7 × 10²² FLOP
How it was established: Third-party estimation

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 Tesla V100 DGXS 16 GB
Chips used: 512
Power draw: 259.1 kW
Compute cost: $60,072

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.

Foundation model: Yes
Why it is tracked: SOTA improvement
Record confidence: Likely
Citations: 979

Sources

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

Reference: CogView: Mastering Text-to-Image Generation via Transformers
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run CogView

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 CogView

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

3.6 GB

Fastest

847 tok/s

CogView is small enough at 4B 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 Q5_K_M and producing around 16.5 tokens per second.

The quickest result comes from a B200 at around 847 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

About this model

CogView was published by Tsinghua University,Alibaba DAMO Academy, in China, in May 2021. The organisation is categorised as academia,Industry.

It works in Image generation, and is recorded as doing text-to-image, Image generation.

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.

How fast it runs, and why

The median result is around 28.4 tokens per second; 776 cards produce text faster than most people read it.

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.

How it was trained

Producing it required around 2.7 × 10²² FLOP of arithmetic, on NVIDIA Tesla V100 DGXS 16 GB, which is a statement about the training budget rather than about inference.

Around 964,800,000,000 tokens went into training it.

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

Step by step

How to choose a GPU for CogView

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 CogView — around 3.6 GB at Q5_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Match the context to your actual use

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for CogView.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of CogView — Q5_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Sort by speed to see how cards rank for CogView. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 847 tok/s.
05

Read the fit column last

A tight fit runs CogView 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 CogView alone — a card is usually bought for more than one model.

Answers

CogView — common questions

When was CogView released?

CogView was published in May 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 CogView used for?

CogView works in Image generation, and is recorded as handling text-to-image, Image generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download CogView?

The weights for CogView 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 CogView?

Around 2.7 × 10²² FLOP, on NVIDIA Tesla V100 DGXS 16 GB. 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 CogView 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 CogView is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run CogView faster?

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

Why does the quantisation differ between cards for CogView?

Because capacity varies, so does how hard CogView has to be squeezed — 3 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these CogView speed estimates?

These are estimates with real error bars. The fastest result here, 508–1,355 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 CogView?

The smallest card in our catalogue that holds CogView is the Tesla C1080, with 4 GB of memory. It runs the model at Q5_K_M using about 3.6 GB, and produces roughly 16.5 tokens per second. 818 cards in total can run it.

How fast is CogView on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 847 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 776 of the cards that can run CogView clear that.

How much VRAM does CogView need?

About 3.6 GB at Q5_K_M 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 CogView on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 5.0 GB and generating roughly 158 tokens per second — a comfortable fit.

Can I run CogView on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 5.0 GB and generating roughly 96.6 tokens per second — a comfortable fit.

Can I run CogView on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 5.0 GB and generating roughly 120 tokens per second — a comfortable fit.

Can I run CogView on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 5.0 GB and generating roughly 142 tokens per second — a comfortable fit.

Is CogView open source?

Its weights are published, so CogView 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 CogView have?

CogView has 4B parameters. "We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to advance this problem.". 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 CogView?

CogView was published by Tsinghua University,Alibaba DAMO Academy, based in China, categorised as academia,Industry.

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