DataGemma TPS calculator

Open weights Google 27.2B parameters September 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

132 cards that can run it

818 cards we hold specifications for

Smallest card that fits

RTX A4500

20 GB · Q4_K_M · 23.0 tok/s

Fastest card

B200

125 tok/s · 180 GB

Which GPUs can run DataGemma?

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

132 cards match

Calculating

					Needs	Quantisation	Fit
125 tok/s 106–149	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	30.3 GB	Q8_0	Comfortable
125 tok/s 106–149	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	30.3 GB	Q8_0	Comfortable
99.5 tok/s 60–159 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	30.3 GB	Q8_0	Comfortable
99.5 tok/s 60–159 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	30.3 GB	Q8_0	Comfortable
79.6 tok/s 48–127 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	30.3 GB	Q8_0	Comfortable
76.1 tok/s 65–91	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	30.3 GB	Q8_0	Comfortable
76.1 tok/s 65–91	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	30.3 GB	Q8_0	Comfortable
72.9 tok/s 44–117 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	30.3 GB	Q8_0	Comfortable
64.7 tok/s 39–103 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	30.3 GB	Q8_0	Comfortable
64.7 tok/s 39–103 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	30.3 GB	Q8_0	Comfortable
64.7 tok/s 39–103 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	30.3 GB	Q8_0	Comfortable
61.4 tok/s 52–74	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	30.3 GB	Q8_0	Comfortable
52.3 tok/s 44–63	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	30.3 GB	Q8_0	Comfortable
52.3 tok/s 44–63	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	30.3 GB	Q8_0	Comfortable
52.3 tok/s 44–63	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	30.3 GB	Q8_0	Comfortable
52.3 tok/s 44–63	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	30.3 GB	Q8_0	Comfortable
52.3 tok/s 44–63	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	30.3 GB	Q8_0	Comfortable
42.3 tok/s 36–51	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	23.9 GB	Q6_K	Comfortable
42.3 tok/s 36–51	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	23.9 GB	Q6_K	Comfortable
40.5 tok/s 34–49	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	23.9 GB	Q6_K	Comfortable
40.5 tok/s 34–49	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	23.9 GB	Q6_K	Comfortable
39.8 tok/s 24–64 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	30.3 GB	Q8_0	Comfortable
39.8 tok/s 24–64 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	30.3 GB	Q8_0	Comfortable
37.3 tok/s 32–45	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	20.8 GB	Q5_K_M	Tight
33.9 tok/s 29–41	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	20.8 GB	Q5_K_M	Tight

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
Organisation type: Industry
Country: United States of America
Published: 12 September 2024
Authors: Prashanth Radhakrishnan, Jennifer Chen, Bo Xu, Prem Ramaswami, Hannah Pho, Adriana Olmos, James Manyika, R. V. Guha

What it does

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

Domain: Language
Task: Language modeling/generation
Base model: Gemma 2 27B

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: 27.2B
Training data: tokens

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: Google TPU v5e

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)

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: Knowing When to Ask -- Bridging Large Language Models and Data
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run DataGemma

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 DataGemma

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

RTX A4500

Memory needed

17.6 GB

Fastest

125 tok/s

DataGemma reaches a parameter count of 27.2B. That lands in the range a serious desktop card can handle once the weights are compressed. The number of cards we track that can run it: 132.

At the low end it is handled by RTX A4500, with a memory capacity of 20 GB, running it at a compression of Q4_K_M and producing around 23.0 tokens per second.

The quickest result comes from B200, generating roughly 125 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

DataGemma was published by Google, in the country recorded as United States of America, during September 2024. The publishing organisation is categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation.

Rather than being trained from scratch, it is derived from Gemma 2 27B. That is why it shares the base model's general shape and size.

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.

Reading the throughput figures

Half the cards that hold it manage more than 21.5 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 112 of them.

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

Its attention layout is on file, so the memory figures are computed exactly rather than approximated.

Step by step

How to choose a GPU for DataGemma

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 able to hold DataGemma, needing around 17.6 GB at a compression of Q4_K_M. That figure, not the headline performance of a card, 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 DataGemma.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of Q4_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Compare tokens per second, not specifications

Ranking by tokens per second follows memory bandwidth rather than core counts, for DataGemma. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 125 tok/s.
05

Check the fit verdict before buying

Tight means it loads and works with no room to raise the context later, in the case of DataGemma. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
06

Check the card from the other side

Following a card through to its own page shows every other model it can hold, which is the question that follows once you have settled on DataGemma.

Answers

DataGemma — common questions

DataGemma— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation. 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.

DataGemma— where can I download it?

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

DataGemma— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. The nearest miss we calculate falls short by 3.2 GB. Every figure here assumes the whole model is resident on the card.

DataGemma— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 132. So a second card is rarely the answer here.

DataGemma— why does the quantisation differ between cards?

A larger card holds a more accurate copy. The number of compression levels used across the cards that run it: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

DataGemma— how accurate are these speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked, which is why each is published as a range rather than a single number. One example: 106–149 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

DataGemma— what GPU do I need to run it?

The smallest card in our catalogue that holds it is RTX A4500, with a memory capacity of 20 GB. It runs the model at a compression of Q4_K_M using about 17.6 GB, and produces roughly 23.0 tokens per second. The number of cards able to run it in total: 132.

DataGemma— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 125 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 112.

DataGemma— how much VRAM does it need?

It needs about 17.6 GB at a compression of Q4_K_M, 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.

DataGemma— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q5_K_M, using about 20.8 GB and generating roughly 37.3 tokens per second. The fit is tight.

DataGemma— is it open source?

Its weights are published, so it 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.

DataGemma— how many parameters does it have?

It has a parameter count of 27.2B. 27.2B. 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.

DataGemma— who created it?

It was published by Google, based in United States of America, an organisation categorised as industry.

DataGemma— when was it released?

It was published in September 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.

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