iGPT-L TPS calculator

Open weights OpenAI 1.4B parameters June 2020

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 · 27.1 tok/s

Fastest card

B200

2,488 tok/s · 180 GB

Which GPUs can run iGPT-L?

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
2,488 tok/s 1,493–3,980 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	2.2 GB	Q8_0	Comfortable
2,488 tok/s 1,493–3,980 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	2.2 GB	Q8_0	Comfortable
1,986 tok/s 1,192–3,178 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	2.2 GB	Q8_0	Comfortable
1,986 tok/s 1,192–3,178 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	2.2 GB	Q8_0	Comfortable
1,589 tok/s 953–2,542 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	2.2 GB	Q8_0	Comfortable
1,521 tok/s 912–2,433 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.2 GB	Q8_0	Comfortable
1,521 tok/s 912–2,433 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.2 GB	Q8_0	Comfortable
1,455 tok/s 873–2,328 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	2.2 GB	Q8_0	Comfortable
1,292 tok/s 775–2,067 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	2.2 GB	Q8_0	Comfortable
1,292 tok/s 775–2,067 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	2.2 GB	Q8_0	Comfortable
1,292 tok/s 775–2,067 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	2.2 GB	Q8_0	Comfortable
1,225 tok/s 735–1,960 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	2.2 GB	Q8_0	Comfortable
1,045 tok/s 627–1,672 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.2 GB	Q8_0	Comfortable
1,045 tok/s 627–1,672 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	2.2 GB	Q8_0	Comfortable
1,045 tok/s 627–1,672 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	2.2 GB	Q8_0	Comfortable
1,045 tok/s 627–1,672 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.2 GB	Q8_0	Comfortable
1,045 tok/s 627–1,672 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	2.2 GB	Q8_0	Comfortable
796 tok/s 477–1,273 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	2.2 GB	Q8_0	Comfortable
796 tok/s 477–1,273 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	2.2 GB	Q8_0	Comfortable
663 tok/s 398–1,061 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	2.2 GB	Q8_0	Comfortable
649 tok/s 389–1,038 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	2.2 GB	Q8_0	Comfortable
634 tok/s 381–1,015 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	2.2 GB	Q8_0	Comfortable
634 tok/s 381–1,015 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	2.2 GB	Q8_0	Comfortable
634 tok/s 381–1,015 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	2.2 GB	Q8_0	Comfortable
634 tok/s 381–1,015 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	2.2 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: 17 June 2020
Authors: Mark Chen, Alec Radford, Rewon Child, Jeff Wu, Heewoo Jun, Prafulla Dhariwal, David Luan, Ilya Sutskever

What it does

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

Domain: Image generation, Vision
Task: Image completion
Approach: Self-supervised learning

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: 1.4B
Training data: 2,654,208,000 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: 8.9 × 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 Tesla V100 DGXS 32 GB
Chip-hours: 60,000
Compute cost: $30,093

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
Citations: 1,694

Sources

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

Reference: Generative Pretraining from Pixels
Last updated: 1 January 2026

The extremes

The ten fastest GPUs that run iGPT-L

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 iGPT-L

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

2.2 GB

Fastest

2,488 tok/s

iGPT-L is small enough at 1.4B 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 27.1 tokens per second.

Top of the range is the B200, at roughly 2,488 tokens per second thanks to 8,000 GB/s of bandwidth.

About this model

iGPT-L was published by OpenAI, in United States of America, in June 2020. It comes out of industry.

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

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

How fast it runs, and why

The median result is around 69.9 tokens per second; 797 cards produce text faster than most people read it.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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 8.9 × 10²¹ FLOP, on NVIDIA Tesla V100 DGXS 32 GB. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The training set ran to roughly 2,654,208,000 tokens.

Step by step

How to choose a GPU for iGPT-L

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 iGPT-L — around 2.2 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
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 iGPT-L can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

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 iGPT-L by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for iGPT-L follows memory bandwidth, not core counts, which is why the B200 tops it at 2,488 tok/s.
05

Read the fit column last

The fit column separates cards that just manage iGPT-L from those with room to spare. Buy for the second if the context might grow.
06

See what else that card runs

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond iGPT-L.

Answers

iGPT-L — common questions

Can I run iGPT-L on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 2.2 GB and generating roughly 417 tokens per second — a comfortable fit.

Is iGPT-L open source?

Its weights are published, so iGPT-L 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 iGPT-L have?

iGPT-L has 1.4B parameters. source: https://openai.com/blog/image-gpt/#rfref53. 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 iGPT-L?

iGPT-L was published by OpenAI, based in United States of America, categorised as industry.

When was iGPT-L released?

iGPT-L was published in June 2020. 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 iGPT-L used for?

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

Where can I download iGPT-L?

The weights for iGPT-L 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 iGPT-L?

Around 8.9 × 10²¹ FLOP, on NVIDIA Tesla V100 DGXS 32 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 iGPT-L 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 iGPT-L assume it is fully resident.

Would two GPUs run iGPT-L faster?

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

Why does the quantisation differ between cards for iGPT-L?

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

How accurate are these iGPT-L speed estimates?

These are estimates with real error bars. The fastest result here, 1,493–3,980 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 iGPT-L?

The smallest card in our catalogue that holds iGPT-L is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 2.2 GB, and produces roughly 27.1 tokens per second. 818 cards in total can run it.

How fast is iGPT-L on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 2,488 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 797 of the cards that can run iGPT-L clear that.

How much VRAM does iGPT-L need?

About 2.2 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 iGPT-L on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 2.2 GB and generating roughly 463 tokens per second — a comfortable fit.

Can I run iGPT-L on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 2.2 GB and generating roughly 284 tokens per second — a comfortable fit.

Can I run iGPT-L on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 2.2 GB and generating roughly 351 tokens per second — a comfortable fit.

Source

Original publication

Record last updated 1 January 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