Gemma 4 E2B TPS calculator

Open weights Google DeepMind 5.1B parameters April 2026

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 · Q3_K_M · 43.3 tok/s

Fastest card

B200

1,473 tok/s · 180 GB

Which GPUs can run Gemma 4 E2B?

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
1,473 tok/s 884–2,357 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	6.4 GB	Q8_0	Comfortable
1,473 tok/s 884–2,357 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	6.4 GB	Q8_0	Comfortable
1,176 tok/s 706–1,882 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	6.4 GB	Q8_0	Comfortable
1,176 tok/s 706–1,882 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	6.4 GB	Q8_0	Comfortable
941 tok/s 564–1,505 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	6.4 GB	Q8_0	Comfortable
900 tok/s 540–1,441 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	6.4 GB	Q8_0	Comfortable
900 tok/s 540–1,441 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	6.4 GB	Q8_0	Comfortable
862 tok/s 517–1,379 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	6.4 GB	Q8_0	Comfortable
765 tok/s 459–1,224 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	6.4 GB	Q8_0	Comfortable
765 tok/s 459–1,224 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	6.4 GB	Q8_0	Comfortable
765 tok/s 459–1,224 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	6.4 GB	Q8_0	Comfortable
726 tok/s 435–1,161 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	6.4 GB	Q8_0	Comfortable
619 tok/s 371–990 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	6.4 GB	Q8_0	Comfortable
619 tok/s 371–990 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	6.4 GB	Q8_0	Comfortable
619 tok/s 371–990 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	6.4 GB	Q8_0	Comfortable
619 tok/s 371–990 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	6.4 GB	Q8_0	Comfortable
619 tok/s 371–990 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	6.4 GB	Q8_0	Comfortable
471 tok/s 283–754 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	6.4 GB	Q8_0	Comfortable
471 tok/s 283–754 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	6.4 GB	Q8_0	Comfortable
393 tok/s 236–628 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	6.4 GB	Q8_0	Comfortable
384 tok/s 231–615 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	6.4 GB	Q8_0	Comfortable
376 tok/s 225–601 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	6.4 GB	Q8_0	Comfortable
376 tok/s 225–601 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	6.4 GB	Q8_0	Comfortable
376 tok/s 225–601 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	6.4 GB	Q8_0	Comfortable
376 tok/s 225–601 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	6.4 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: Google DeepMind
Organisation type: Industry
Country: United States of America
Published: 2 April 2026

What it does

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

Domain: Language, Multimodal, Audio
Task: Language modeling/generation

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: 5.1B
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)

The extremes

The ten fastest GPUs that run Gemma 4 E2B

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 Gemma 4 E2B

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 it takes to run this model

Minimum card

Tesla C1080

Memory needed

3.4 GB

Fastest

1,473 tok/s

Gemma 4 E2B reaches a parameter count of 5.1B. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 818.

The smallest card that holds it is Tesla C1080, with a memory capacity of 4 GB, running it at a compression of Q3_K_M and producing around 43.3 tokens per second.

Top of the range is B200, generating roughly 1,473 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

Gemma 4 E2B was published by Google DeepMind, in the country recorded as United States of America, during April 2026. The category the publisher falls under is industry.

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

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

Reading the throughput figures

The median result is around 61.6 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 802 of them.

This is a mixture-of-experts model, which routes each token through only part of itself. It therefore generates far faster than its total size suggests — while still needing every parameter resident in memory, so it is quick without being cheap to hold.

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 Gemma 4 E2B

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 Gemma 4 E2B, needing around 3.4 GB at a compression of Q3_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 Gemma 4 E2B.
03

Set a quality floor

Each card runs the least-compressed copy it can hold, reaching a compression of Q3_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

Sort by speed

Ranking by tokens per second follows memory bandwidth rather than core counts, for Gemma 4 E2B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 1,473 tok/s.
05

Look at the headroom, not just the fit

Tight means it loads and works with no room to raise the context later, in the case of Gemma 4 E2B. 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

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. A card is usually bought for more than one model, so it is worth a look before buying for Gemma 4 E2B.

Answers

Gemma 4 E2B — common questions

Gemma 4 E2B— how much VRAM does it need?

It needs about 3.4 GB at a compression of Q3_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.

Gemma 4 E2B— can I run it on a GPU holding 8 GB?

Yes. The card CMP 170HX 8 GB, holding 8 GB, runs it at a compression of Q8_0, using about 6.4 GB and generating roughly 274 tokens per second. The fit is tight.

Gemma 4 E2B— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of Q8_0, using about 6.4 GB and generating roughly 168 tokens per second. The fit is comfortable.

Gemma 4 E2B— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q8_0, using about 6.4 GB and generating roughly 208 tokens per second. The fit is comfortable.

Gemma 4 E2B— 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 Q8_0, using about 6.4 GB and generating roughly 247 tokens per second. The fit is comfortable.

Gemma 4 E2B— 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.

Gemma 4 E2B— how many parameters does it have?

It has a parameter count of 5.1B. 2.3B effective of 5.1B raw including embeddings. 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.

Gemma 4 E2B— who created it?

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

Gemma 4 E2B— when was it released?

It was published in April 2026.

Gemma 4 E2B— what is it used for?

It works in the domain of Language, Multimodal, Audio, and is recorded as handling the task of language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Gemma 4 E2B— 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.

Gemma 4 E2B— can I run it 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 model is rarely worth using. Every figure here assumes the whole model is resident on the card.

Gemma 4 E2B— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 818. So a second card is rarely the answer here.

Gemma 4 E2B— 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.

Gemma 4 E2B— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 884–2,357 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Gemma 4 E2B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Tesla C1080, with a memory capacity of 4 GB. It runs the model at a compression of Q3_K_M using about 3.4 GB, and produces roughly 43.3 tokens per second. The number of cards able to run it in total: 818.

Gemma 4 E2B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 1,473 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: 802.

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