Derm Foundational Model TPS calculator

Open weights Google Research 928M parameters March 2024

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 · 39.7 tok/s

Fastest card

B200

3,651 tok/s · 180 GB

Which GPUs can run Derm Foundational Model?

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
3,651 tok/s 2,191–5,842 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.7 GB	Q8_0	Comfortable
3,651 tok/s 2,191–5,842 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.7 GB	Q8_0	Comfortable
2,916 tok/s 1,749–4,665 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.7 GB	Q8_0	Comfortable
2,916 tok/s 1,749–4,665 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.7 GB	Q8_0	Comfortable
2,332 tok/s 1,399–3,731 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.7 GB	Q8_0	Comfortable
2,232 tok/s 1,339–3,571 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.7 GB	Q8_0	Comfortable
2,232 tok/s 1,339–3,571 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.7 GB	Q8_0	Comfortable
2,136 tok/s 1,282–3,417 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.7 GB	Q8_0	Comfortable
1,896 tok/s 1,137–3,033 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.7 GB	Q8_0	Comfortable
1,896 tok/s 1,137–3,033 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.7 GB	Q8_0	Comfortable
1,896 tok/s 1,137–3,033 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.7 GB	Q8_0	Comfortable
1,798 tok/s 1,079–2,877 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.7 GB	Q8_0	Comfortable
1,533 tok/s 920–2,454 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.7 GB	Q8_0	Comfortable
1,533 tok/s 920–2,454 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.7 GB	Q8_0	Comfortable
1,533 tok/s 920–2,454 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.7 GB	Q8_0	Comfortable
1,533 tok/s 920–2,454 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.7 GB	Q8_0	Comfortable
1,533 tok/s 920–2,454 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.7 GB	Q8_0	Comfortable
1,168 tok/s 701–1,868 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.7 GB	Q8_0	Comfortable
1,168 tok/s 701–1,868 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.7 GB	Q8_0	Comfortable
973 tok/s 584–1,557 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.7 GB	Q8_0	Comfortable
952 tok/s 571–1,524 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.7 GB	Q8_0	Comfortable
931 tok/s 559–1,490 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.7 GB	Q8_0	Comfortable
931 tok/s 559–1,490 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.7 GB	Q8_0	Comfortable
931 tok/s 559–1,490 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.7 GB	Q8_0	Comfortable
931 tok/s 559–1,490 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.7 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 Research
Organisation type: Industry
Country: United States of America
Published: 8 March 2024
Authors: Dave Steiner, Rory Pilgrim

What it does

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

Domain: Vision, Medicine
Task: Image embedding, Medical diagnosis, Cancer diagnosis, Image classification
Base model: Big Transfer (BiT-M)

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: 928M
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 (restricted use)
Training code: Open source
Hugging Face: google

How it is classified

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

Record confidence: Likely

Sources

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

Reference: Health-specific embedding tools for dermatology and pathology
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Derm Foundational Model

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 Derm Foundational Model

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

1.7 GB

Fastest

3,651 tok/s

Derm Foundational Model is small enough at 928M 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 39.7 tokens per second.

A B200 is the fastest we calculate for it: about 3,651 tokens per second, from 8,000 GB/s of memory bandwidth.

Where it came from

Derm Foundational Model was published by Google Research, in United States of America, in March 2024. It comes out of industry.

It works in Vision, Medicine, and is recorded as doing image embedding, Medical diagnosis, Cancer diagnosis, Image classification.

It builds on Big Transfer (BiT-M), which is why it shares that model's general shape and size.

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. It is published under the google organisation on Hugging Face.

Understanding the speeds

Half the cards that hold it manage more than 102.5 tokens per second, and 806 exceed reading speed outright.

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.

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.

Step by step

How to choose a GPU for Derm Foundational Model

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

Look at what Derm Foundational Model actually needs — around 1.7 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

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

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of Derm Foundational Model — 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

Ranking by tokens per second for Derm Foundational Model follows memory bandwidth, not core counts, which is why the B200 tops it at 3,651 tok/s.
05

Read the fit column last

A tight fit runs Derm Foundational Model but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Open the card you have settled on

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for Derm Foundational Model alone — a card is usually bought for more than one model.

Answers

Derm Foundational Model — common questions

Would two GPUs run Derm Foundational Model faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold Derm Foundational Model on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Derm Foundational Model?

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

How accurate are these Derm Foundational Model 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 2,191–5,842 tok/s on the B200 rather than a single number.

What GPU do I need to run Derm Foundational Model?

The smallest card in our catalogue that holds Derm Foundational Model is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.7 GB, and produces roughly 39.7 tokens per second. 818 cards in total can run it.

How fast is Derm Foundational Model on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 3,651 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 806 of the cards that can run Derm Foundational Model clear that.

How much VRAM does Derm Foundational Model need?

About 1.7 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 Derm Foundational Model on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.7 GB and generating roughly 680 tokens per second — a comfortable fit.

Can I run Derm Foundational Model on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.7 GB and generating roughly 416 tokens per second — a comfortable fit.

Can I run Derm Foundational Model on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.7 GB and generating roughly 516 tokens per second — a comfortable fit.

Can I run Derm Foundational Model on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.7 GB and generating roughly 612 tokens per second — a comfortable fit.

Is Derm Foundational Model open source?

Its weights are published, so Derm Foundational Model 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 Derm Foundational Model have?

Derm Foundational Model has 928M parameters. "The model is a BiT-M ResNet101x3" BiT-M has 928M parameters, I assume same here. 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 Derm Foundational Model?

Derm Foundational Model was published by Google Research, based in United States of America, categorised as industry.

When was Derm Foundational Model released?

Derm Foundational Model was published in March 2024. 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 Derm Foundational Model used for?

Derm Foundational Model works in Vision, Medicine, and is recorded as handling image embedding, Medical diagnosis, Cancer diagnosis, Image classification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Derm Foundational Model?

Its weights are published under the google organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

Can I run Derm Foundational Model if it does not fit in my GPU?

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

Source

Original publication

Record last updated 28 November 2025

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