German ELECTRA Large TPS calculator

Open weights deepset,Bayerische Staatsbibliothek Muenchen 335M parameters October 2020

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 · 110 tok/s

Fastest card

B200

10,114 tok/s · 180 GB

Which GPUs can run German ELECTRA Large?

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
10,114 tok/s 6,068–16,183 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.1 GB	Q8_0	Comfortable
10,114 tok/s 6,068–16,183 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.1 GB	Q8_0	Comfortable
8,076 tok/s 4,846–12,922 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.1 GB	Q8_0	Comfortable
8,076 tok/s 4,846–12,922 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.1 GB	Q8_0	Comfortable
6,459 tok/s 3,875–10,335 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.1 GB	Q8_0	Comfortable
6,182 tok/s 3,709–9,892 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.1 GB	Q8_0	Comfortable
6,182 tok/s 3,709–9,892 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.1 GB	Q8_0	Comfortable
5,917 tok/s 3,550–9,467 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.1 GB	Q8_0	Comfortable
5,251 tok/s 3,151–8,402 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.1 GB	Q8_0	Comfortable
5,251 tok/s 3,151–8,402 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.1 GB	Q8_0	Comfortable
5,251 tok/s 3,151–8,402 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.1 GB	Q8_0	Comfortable
4,981 tok/s 2,989–7,970 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
4,248 tok/s 2,549–6,797 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
4,248 tok/s 2,549–6,797 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.1 GB	Q8_0	Comfortable
4,248 tok/s 2,549–6,797 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
4,248 tok/s 2,549–6,797 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
4,248 tok/s 2,549–6,797 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
3,235 tok/s 1,941–5,175 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.1 GB	Q8_0	Comfortable
3,235 tok/s 1,941–5,175 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.1 GB	Q8_0	Comfortable
2,695 tok/s 1,617–4,313 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.1 GB	Q8_0	Comfortable
2,638 tok/s 1,583–4,221 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.1 GB	Q8_0	Comfortable
2,579 tok/s 1,547–4,127 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.1 GB	Q8_0	Comfortable
2,579 tok/s 1,547–4,127 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.1 GB	Q8_0	Comfortable
2,579 tok/s 1,547–4,127 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.1 GB	Q8_0	Comfortable
2,579 tok/s 1,547–4,127 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.1 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: deepset,Bayerische Staatsbibliothek Muenchen
Organisation type: Industry,Government
Country: Germany
Published: 21 October 2020
Authors: Branden Chan, Stefan Schweter, Timo Möller

What it does

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

Domain: Language
Task: Document classification, Named entity recognition (NER), Text classification

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: 335M
Training data: 36,383,733,333 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.

Training compute: 1.4 × 10²¹ FLOP
How it was established: Hardware,Operation counting

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 v3
Chips used: 64
Chip-hours: 10,752
Wall-clock time: 168 hours (7 days)
Power draw: 58.6 kW
Compute cost: $2,392

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)
Training code: Unreleased
Hugging Face: deepset

How it is classified

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

Why it is tracked: SOTA improvement
Record confidence: Confident
Citations: 333

Sources

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

Reference: German's Next Language Model
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run German ELECTRA Large

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 German ELECTRA Large

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

1.1 GB

Fastest

10,114 tok/s

German ELECTRA Large is small enough at 335M 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 110 tokens per second.

At the other end, a B200 generates roughly 10,114 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

What this model is

German ELECTRA Large was published by deepset,Bayerische Staatsbibliothek Muenchen, in Germany, in October 2020. industry,Government is the category the publisher falls under.

It works in Language, and is recorded as doing document classification, Named entity recognition (NER), Text classification.

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 deepset organisation on Hugging Face.

What decides the speed

The median result is around 284.0 tokens per second; 818 cards produce text faster than most people read it.

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.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

What went into building it

Training it took roughly 1.4 × 10²¹ FLOP of computation, on Google TPU v3 — a measure of what producing the model cost, not of how fast it answers.

Around 36,383,733,333 tokens went into training it.

The reason it appears in this catalogue at all is sOTA improvement.

Step by step

How to choose a GPU for German ELECTRA Large

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

Look at what German ELECTRA Large actually needs — around 1.1 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context German ELECTRA Large can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of German ELECTRA Large — 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 German ELECTRA Large follows memory bandwidth, not core counts, which is why the B200 tops it at 10,114 tok/s.
05

Check the fit verdict before buying

A tight fit runs German ELECTRA Large 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

Following a card through to its own page shows every other model it can hold, which is the question that follows once German ELECTRA Large is settled.

Answers

German ELECTRA Large — common questions

Why does the quantisation differ between cards for German ELECTRA Large?

Each card is shown running the least-compressed copy it can hold, and German ELECTRA Large appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these German ELECTRA Large speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 6,068–16,183 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 German ELECTRA Large?

The smallest card in our catalogue that holds German ELECTRA Large is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.1 GB, and produces roughly 110 tokens per second. 818 cards in total can run it.

How fast is German ELECTRA Large on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 10,114 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 818 of the cards that can run German ELECTRA Large clear that.

How much VRAM does German ELECTRA Large need?

About 1.1 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 German ELECTRA Large on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.1 GB and generating roughly 1,884 tokens per second — a comfortable fit.

Can I run German ELECTRA Large on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.1 GB and generating roughly 1,154 tokens per second — a comfortable fit.

Can I run German ELECTRA Large on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.1 GB and generating roughly 1,429 tokens per second — a comfortable fit.

Can I run German ELECTRA Large on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.1 GB and generating roughly 1,694 tokens per second — a comfortable fit.

Is German ELECTRA Large open source?

Its weights are published, so German ELECTRA Large 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 German ELECTRA Large have?

German ELECTRA Large has 335M parameters. 335M from Table 5. 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 German ELECTRA Large?

German ELECTRA Large was published by deepset,Bayerische Staatsbibliothek Muenchen, based in Germany, categorised as industry,Government.

When was German ELECTRA Large released?

German ELECTRA Large was published in October 2020. 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 German ELECTRA Large used for?

German ELECTRA Large works in Language, and is recorded as handling document classification, Named entity recognition (NER), Text classification. 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.

Where can I download German ELECTRA Large?

Its weights are published under the deepset 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 German ELECTRA Large?

Around 1.4 × 10²¹ FLOP, on Google TPU v3. 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 German ELECTRA Large if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down. Our figures for German ELECTRA Large assume it is fully resident.

Would two GPUs run German ELECTRA Large faster?

Two cards buy memory rather than speed. That matters for German ELECTRA Large only if one card cannot hold it — 818 can, so a second adds little.

Source

Original publication

Record last updated 25 May 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