AMDIM TPS calculator

Open weights Microsoft Research 626M parameters June 2019

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 · 58.9 tok/s

Fastest card

B200

5,413 tok/s · 180 GB

Which GPUs can run AMDIM?

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
5,413 tok/s 3,248–8,660 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.4 GB	Q8_0	Comfortable
5,413 tok/s 3,248–8,660 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.4 GB	Q8_0	Comfortable
4,322 tok/s 2,593–6,915 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.4 GB	Q8_0	Comfortable
4,322 tok/s 2,593–6,915 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.4 GB	Q8_0	Comfortable
3,457 tok/s 2,074–5,531 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.4 GB	Q8_0	Comfortable
3,308 tok/s 1,985–5,293 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.4 GB	Q8_0	Comfortable
3,308 tok/s 1,985–5,293 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.4 GB	Q8_0	Comfortable
3,166 tok/s 1,900–5,066 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.4 GB	Q8_0	Comfortable
2,810 tok/s 1,686–4,496 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.4 GB	Q8_0	Comfortable
2,810 tok/s 1,686–4,496 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.4 GB	Q8_0	Comfortable
2,810 tok/s 1,686–4,496 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.4 GB	Q8_0	Comfortable
2,666 tok/s 1,599–4,265 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.4 GB	Q8_0	Comfortable
2,273 tok/s 1,364–3,637 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.4 GB	Q8_0	Comfortable
2,273 tok/s 1,364–3,637 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.4 GB	Q8_0	Comfortable
2,273 tok/s 1,364–3,637 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.4 GB	Q8_0	Comfortable
2,273 tok/s 1,364–3,637 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.4 GB	Q8_0	Comfortable
2,273 tok/s 1,364–3,637 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.4 GB	Q8_0	Comfortable
1,731 tok/s 1,039–2,769 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.4 GB	Q8_0	Comfortable
1,731 tok/s 1,039–2,769 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.4 GB	Q8_0	Comfortable
1,442 tok/s 865–2,308 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.4 GB	Q8_0	Comfortable
1,412 tok/s 847–2,259 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.4 GB	Q8_0	Comfortable
1,380 tok/s 828–2,208 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.4 GB	Q8_0	Comfortable
1,380 tok/s 828–2,208 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.4 GB	Q8_0	Comfortable
1,380 tok/s 828–2,208 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.4 GB	Q8_0	Comfortable
1,380 tok/s 828–2,208 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.4 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: Microsoft Research
Organisation type: Industry
Country: United States of America
Published: 3 June 2019
Authors: Philip Bachman, R Devon Hjelm, William Buchwalter

What it does

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

Domain: Vision, Image generation
Task: Image completion
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: 626M
Training data: tokens

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.

Citations: 1,644

Sources

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

Reference: Learning Representations by Maximizing Mutual Information Across Views
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run AMDIM

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 AMDIM

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

Hardware requirements in practice

Minimum card

Tesla C1080

Memory needed

1.4 GB

Fastest

5,413 tok/s

AMDIM is small enough at 626M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The entry point is the Tesla C1080: 4 GB of memory, Q8_0 compression, roughly 58.9 tokens per second.

The quickest result comes from a B200 at around 5,413 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

What this model is

AMDIM was published by Microsoft Research, in United States of America, in June 2019. industry is the category the publisher falls under.

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

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.

What decides the speed

Across every card that can run it, the middle of the range is about 152.0 tokens per second, and 809 of them clear the ten tokens per second that roughly matches reading speed.

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.

Step by step

How to choose a GPU for AMDIM

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 AMDIM — around 1.4 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
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 AMDIM 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 AMDIM — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Ranking by tokens per second for AMDIM follows memory bandwidth, not core counts, which is why the B200 tops it at 5,413 tok/s.
05

Read the fit column last

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

Answers

AMDIM — common questions

Can I run AMDIM if it does not fit in my GPU?

It can be split between the card and system memory, but AMDIM generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run AMDIM faster?

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

Why does the quantisation differ between cards for AMDIM?

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

How accurate are these AMDIM speed estimates?

These are estimates with real error bars. The fastest result here, 3,248–8,660 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 AMDIM?

The smallest card in our catalogue that holds AMDIM is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.4 GB, and produces roughly 58.9 tokens per second. 818 cards in total can run it.

How fast is AMDIM on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 5,413 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 809 of the cards that can run AMDIM clear that.

How much VRAM does AMDIM need?

About 1.4 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 AMDIM on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.4 GB and generating roughly 1,008 tokens per second — a comfortable fit.

Can I run AMDIM on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.4 GB and generating roughly 617 tokens per second — a comfortable fit.

Can I run AMDIM on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.4 GB and generating roughly 765 tokens per second — a comfortable fit.

Can I run AMDIM on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.4 GB and generating roughly 907 tokens per second — a comfortable fit.

Is AMDIM open source?

Its weights are published, so AMDIM 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 AMDIM have?

AMDIM has 626M parameters. source: https://openai.com/blog/image-gpt/#rfref13e. 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 AMDIM?

AMDIM was published by Microsoft Research, based in United States of America, categorised as industry.

When was AMDIM released?

AMDIM was published in June 2019. 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 AMDIM used for?

AMDIM works in Vision, Image generation, and is recorded as handling image completion. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Where can I download AMDIM?

The weights for AMDIM are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

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