Prithvi-EO-2.0 600M TPS calculator

Open weights IBM Research,NASA,University of Alabama,University of Iceland,Forschungszentrum Julich,Virginia Tech (Virginia Polytechnic Institute and State University),Arizona State University,Oregon State University,Boston University,University of California (UC) Berkeley,Julich Supercomputing Center 600M parameters February 2025

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 · 61.4 tok/s

Fastest card

B200

5,647 tok/s · 180 GB

Which GPUs can run Prithvi-EO-2.0 600M?

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
5,647 tok/s 3,388–9,035 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.3 GB	Q8_0	Comfortable
5,647 tok/s 3,388–9,035 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.3 GB	Q8_0	Comfortable
4,509 tok/s 2,706–7,215 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.3 GB	Q8_0	Comfortable
4,509 tok/s 2,706–7,215 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.3 GB	Q8_0	Comfortable
3,606 tok/s 2,164–5,770 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.3 GB	Q8_0	Comfortable
3,452 tok/s 2,071–5,523 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.3 GB	Q8_0	Comfortable
3,452 tok/s 2,071–5,523 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.3 GB	Q8_0	Comfortable
3,304 tok/s 1,982–5,286 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.3 GB	Q8_0	Comfortable
2,932 tok/s 1,759–4,691 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.3 GB	Q8_0	Comfortable
2,932 tok/s 1,759–4,691 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.3 GB	Q8_0	Comfortable
2,932 tok/s 1,759–4,691 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.3 GB	Q8_0	Comfortable
2,781 tok/s 1,669–4,450 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.3 GB	Q8_0	Comfortable
2,372 tok/s 1,423–3,795 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.3 GB	Q8_0	Comfortable
2,372 tok/s 1,423–3,795 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.3 GB	Q8_0	Comfortable
2,372 tok/s 1,423–3,795 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.3 GB	Q8_0	Comfortable
2,372 tok/s 1,423–3,795 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.3 GB	Q8_0	Comfortable
2,372 tok/s 1,423–3,795 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.3 GB	Q8_0	Comfortable
1,806 tok/s 1,084–2,889 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.3 GB	Q8_0	Comfortable
1,806 tok/s 1,084–2,889 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.3 GB	Q8_0	Comfortable
1,505 tok/s 903–2,408 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.3 GB	Q8_0	Comfortable
1,473 tok/s 884–2,357 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.3 GB	Q8_0	Comfortable
1,440 tok/s 864–2,304 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.3 GB	Q8_0	Comfortable
1,440 tok/s 864–2,304 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.3 GB	Q8_0	Comfortable
1,440 tok/s 864–2,304 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.3 GB	Q8_0	Comfortable
1,440 tok/s 864–2,304 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.3 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: IBM Research,NASA,University of Alabama,University of Iceland,Forschungszentrum Julich,Virginia Tech (Virginia Polytechnic Institute and State University),Arizona State University,Oregon State University,Boston University,University of California (UC) Berkeley,Julich Supercomputing Center
Organisation type: Industry,Government,Academia,Academia,Government,Academia,Academia,Academia,Academia,Academia,Government
Country: United States of America, Iceland, Germany
Published: 3 February 2025
Authors: Daniela Szwarcman, Sujit Roy, Paolo Fraccaro, Þorsteinn Elí Gíslason, Benedikt Blumenstiel, Rinki Ghosal, Pedro Henrique de Oliveira, Joao Lucas de Sousa Almeida, Rocco Sedona, Yanghui Kang, Srija Chakraborty, Sizhe Wang, Carlos Gomes, Ankur Kumar, Myscon Truong, Denys Godwin, Hyunho Lee, Chia-Yu Hsu, Ata Akbari Asanjan, Besart Mujeci, Disha Shidham, Trevor Keenan, Paulo Arevalo, Wenwen Li, Hamed …

What it does

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

Domain: Earth science

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: 600M
Training data: tokens
Epochs: 400

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 × 10²² 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 A100
Chips used: 240
Chip-hours: 58,000
Power draw: 188.5 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)
Hugging Face: ibm-nasa-geospatial

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: Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Prithvi-EO-2.0 600M

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 Prithvi-EO-2.0 600M

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

1.3 GB

Fastest

5,647 tok/s

Prithvi-EO-2.0 600M is small enough at 600M 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 61.4 tokens per second.

Top of the range is the B200, at roughly 5,647 tokens per second thanks to 8,000 GB/s of bandwidth.

About this model

Prithvi-EO-2.0 600M was published by IBM Research,NASA,University of Alabama,University of Iceland,Forschungszentrum Julich,Virginia Tech (Virginia Polytechnic Institute and State University),Arizona State University,Oregon State University,Boston University,University of California (UC) Berkeley,Julich Supercomputing Center, in United States of America, in February 2025. industry,Government,Academia,Academia,Government,Academia,Academia,Academia,Academia,Academia,Government is the category the publisher falls under.

It works in Earth science.

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. It is published under the ibm-nasa-geospatial organisation on Hugging Face.

How fast it runs, and why

The median result is around 158.6 tokens per second; 809 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.

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 2 × 10²² FLOP of computation, on NVIDIA A100 — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for Prithvi-EO-2.0 600M

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 Prithvi-EO-2.0 600M — around 1.3 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Prithvi-EO-2.0 600M can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Compression is what makes Prithvi-EO-2.0 600M fit smaller cards, at some cost in accuracy — Q8_0 on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for Prithvi-EO-2.0 600M follows memory bandwidth, not core counts, which is why the B200 tops it at 5,647 tok/s.
05

Read the fit column last

The fit column separates cards that just manage Prithvi-EO-2.0 600M from those with room to spare. Buy for the second if the context might grow.
06

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Prithvi-EO-2.0 600M.

Answers

Prithvi-EO-2.0 600M — common questions

Why does the quantisation differ between cards for Prithvi-EO-2.0 600M?

Because capacity varies, so does how hard Prithvi-EO-2.0 600M has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Prithvi-EO-2.0 600M speed estimates?

These are estimates with real error bars. The fastest result here, 3,388–9,035 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 Prithvi-EO-2.0 600M?

The smallest card in our catalogue that holds Prithvi-EO-2.0 600M is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.3 GB, and produces roughly 61.4 tokens per second. 818 cards in total can run it.

How fast is Prithvi-EO-2.0 600M on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 5,647 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 Prithvi-EO-2.0 600M clear that.

How much VRAM does Prithvi-EO-2.0 600M need?

About 1.3 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 Prithvi-EO-2.0 600M on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.3 GB and generating roughly 1,052 tokens per second — a comfortable fit.

Can I run Prithvi-EO-2.0 600M on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.3 GB and generating roughly 644 tokens per second — a comfortable fit.

Can I run Prithvi-EO-2.0 600M on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.3 GB and generating roughly 798 tokens per second — a comfortable fit.

Can I run Prithvi-EO-2.0 600M on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.3 GB and generating roughly 946 tokens per second — a comfortable fit.

Is Prithvi-EO-2.0 600M open source?

Its weights are published, so Prithvi-EO-2.0 600M 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 Prithvi-EO-2.0 600M have?

Prithvi-EO-2.0 600M has 600M parameters. 600M. 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 Prithvi-EO-2.0 600M?

Prithvi-EO-2.0 600M was published by IBM Research,NASA,University of Alabama,University of Iceland,Forschungszentrum Julich,Virginia Tech (Virginia Polytechnic Institute and State University),Arizona State University,Oregon State University,Boston University,University of California (UC) Berkeley,Julich Supercomputing Center, based in United States of America, categorised as industry,Government,Academia,Academia,Government,Academia,Academia,Academia,Academia,Academia,Government.

When was Prithvi-EO-2.0 600M released?

Prithvi-EO-2.0 600M was published in February 2025.

What is Prithvi-EO-2.0 600M used for?

Prithvi-EO-2.0 600M works in Earth science. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Prithvi-EO-2.0 600M?

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

How much compute was used to train Prithvi-EO-2.0 600M?

Around 2 × 10²² FLOP, on NVIDIA A100. 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 Prithvi-EO-2.0 600M 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 Prithvi-EO-2.0 600M is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run Prithvi-EO-2.0 600M faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run Prithvi-EO-2.0 600M alone, the case for pairing is weak.

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