T5Gemma (Gemma 9B-9B) TPS calculator

Open weights Google DeepMind 16.7B parameters April 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

306 cards that can run it

818 cards we hold specifications for

Smallest card that fits

P102-101

10 GB · Q3_K_M · 18.6 tok/s

Fastest card

B200

203 tok/s · 180 GB

Which GPUs can run T5Gemma (Gemma 9B-9B)?

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

306 cards match

Calculating

					Needs	Quantisation	Fit
203 tok/s 122–325 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	18.6 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	18.6 GB	Q8_0	Comfortable
162 tok/s 97–259 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	18.6 GB	Q8_0	Comfortable
162 tok/s 97–259 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	18.6 GB	Q8_0	Comfortable
130 tok/s 78–207 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	18.6 GB	Q8_0	Comfortable
124 tok/s 74–198 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	18.6 GB	Q8_0	Comfortable
124 tok/s 74–198 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	18.6 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	18.6 GB	Q8_0	Comfortable
107 tok/s 64–171 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.9 GB	Q3_K_M	Tight
105 tok/s 63–169 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	18.6 GB	Q8_0	Comfortable
105 tok/s 63–169 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	18.6 GB	Q8_0	Comfortable
105 tok/s 63–169 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	18.6 GB	Q8_0	Comfortable
99.9 tok/s 60–160 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	18.6 GB	Q8_0	Comfortable
85.2 tok/s 51–136 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	18.6 GB	Q8_0	Comfortable
85.2 tok/s 51–136 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	18.6 GB	Q8_0	Comfortable
85.2 tok/s 51–136 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	18.6 GB	Q8_0	Comfortable
85.2 tok/s 51–136 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	18.6 GB	Q8_0	Comfortable
85.2 tok/s 51–136 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	18.6 GB	Q8_0	Comfortable
64.9 tok/s 39–104 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	18.6 GB	Q8_0	Comfortable
64.9 tok/s 39–104 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	18.6 GB	Q8_0	Comfortable
56.8 tok/s 34–91 · low confidence	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	9.8 GB	IQ4_XS	Tight
56.8 tok/s 34–91 · low confidence	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	9.8 GB	IQ4_XS	Tight
54.1 tok/s 32–87 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	18.6 GB	Q8_0	Comfortable
52.9 tok/s 32–85 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	18.6 GB	Q8_0	Comfortable
52.0 tok/s 31–83 · low confidence	CMP 90HX NVIDIA	10 GB	760 GB/s	Jul 2021	8.9 GB	Q3_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 DeepMind
Organisation type: Industry
Country: United States of America
Published: 8 April 2025
Authors: Biao Zhang, Fedor Moiseev, Joshua Ainslie, Paul Suganthan, Min Ma, Surya Bhupatiraju, Fede Lebron, Orhan Firat, Armand Joulin, Zhe Dong

What it does

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

Domain: Language
Task: Semantic embedding, Language modeling/generation, Question answering
Base model: Gemma 2 9B

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: 16.7B
Training data: 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.

How it was established: Operation counting
Fine-tuning compute: 2 × 10²³ FLOP

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: Unreleased
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: Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation
Last updated: 11 February 2026

The extremes

The ten fastest GPUs that run T5Gemma (Gemma 9B-9B)

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 T5Gemma (Gemma 9B-9B)

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

P102-101

Memory needed

8.9 GB

Fastest

203 tok/s

T5Gemma (Gemma 9B-9B) is small enough at 16.7B parameters that hardware is rarely the obstacle — 306 of the cards we track can run it, including cards several years old.

At the low end, a P102-101 handles it — 10 GB, at Q3_K_M, for about 18.6 tokens per second.

A B200 is the fastest we calculate for it: about 203 tokens per second, from 8,000 GB/s of memory bandwidth.

Where it came from

T5Gemma (Gemma 9B-9B) was published by Google DeepMind, in United States of America, in April 2025. industry is the category the publisher falls under.

It works in Language, and is recorded as doing semantic embedding, Language modeling/generation, Question answering.

It is derived from Gemma 2 9B rather than trained from scratch, which is the usual way a specialised model is produced.

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

Across every card that can run it, the middle of the range is about 20.9 tokens per second, and 268 of them clear the ten tokens per second that roughly matches reading speed.

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.

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 T5Gemma (Gemma 9B-9B)

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Read the memory figure first

The table lists every card that can hold T5Gemma (Gemma 9B-9B) — around 8.9 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason T5Gemma (Gemma 9B-9B) stops fitting a card that seemed fine.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage T5Gemma (Gemma 9B-9B) by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Sort by speed to see how cards rank for T5Gemma (Gemma 9B-9B). It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 203 tok/s.
05

Check the fit verdict before buying

Tight means T5Gemma (Gemma 9B-9B) loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
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 T5Gemma (Gemma 9B-9B) alone — a card is usually bought for more than one model.

Answers

T5Gemma (Gemma 9B-9B) — common questions

Would two GPUs run T5Gemma (Gemma 9B-9B) faster?

Two cards buy memory rather than speed. That matters for T5Gemma (Gemma 9B-9B) only if one card cannot hold it — 306 can, so a second adds little.

Why does the quantisation differ between cards for T5Gemma (Gemma 9B-9B)?

Each card is shown running the least-compressed copy it can hold, and T5Gemma (Gemma 9B-9B) appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these T5Gemma (Gemma 9B-9B) speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 122–325 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run T5Gemma (Gemma 9B-9B)?

The smallest card in our catalogue that holds T5Gemma (Gemma 9B-9B) is the P102-101, with 10 GB of memory. It runs the model at Q3_K_M using about 8.9 GB, and produces roughly 18.6 tokens per second. 306 cards in total can run it.

How fast is T5Gemma (Gemma 9B-9B) on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 203 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 268 of the cards that can run T5Gemma (Gemma 9B-9B) clear that.

How much VRAM does T5Gemma (Gemma 9B-9B) need?

About 8.9 GB at Q3_K_M 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 T5Gemma (Gemma 9B-9B) on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at IQ4_XS, using about 9.8 GB and generating roughly 56.8 tokens per second — a tight fit.

Can I run T5Gemma (Gemma 9B-9B) on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q5_K_M, using about 12.7 GB and generating roughly 51.2 tokens per second — a tight fit.

Can I run T5Gemma (Gemma 9B-9B) on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 18.6 GB and generating roughly 34.0 tokens per second — a tight fit.

Is T5Gemma (Gemma 9B-9B) open source?

Its weights are published, so T5Gemma (Gemma 9B-9B) 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 T5Gemma (Gemma 9B-9B) have?

T5Gemma (Gemma 9B-9B) has 16.7B parameters. 16.7B. 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 T5Gemma (Gemma 9B-9B)?

T5Gemma (Gemma 9B-9B) was published by Google DeepMind, based in United States of America, categorised as industry.

When was T5Gemma (Gemma 9B-9B) released?

T5Gemma (Gemma 9B-9B) was published in April 2025.

What is T5Gemma (Gemma 9B-9B) used for?

T5Gemma (Gemma 9B-9B) works in Language, and is recorded as handling semantic embedding, Language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download T5Gemma (Gemma 9B-9B)?

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 T5Gemma (Gemma 9B-9B) 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 T5Gemma (Gemma 9B-9B) is rarely worth using — the nearest miss we calculate is short by 3.6 GB. Every figure here assumes the whole model is on the card.

Source

Original publication

Record last updated 11 February 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