Aya TPS calculator

Open weights Cohere for AI,Brown University,Cohere,Carnegie Mellon University (CMU),Massachusetts Institute of Technology (MIT) 13B parameters February 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

509 of 818 cards that can run it

Smallest card that fits

Xeon Phi 5110P

8 GB · Q3_K_M · 18.3 tok/s

Fastest card

B200

261 tok/s · 180 GB

Which GPUs can run Aya?

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

509 cards match

Calculating

					Needs	Quantisation	Fit
261 tok/s 156–417 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	14.6 GB	Q8_0	Comfortable
261 tok/s 156–417 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	14.6 GB	Q8_0	Comfortable
208 tok/s 125–333 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	14.6 GB	Q8_0	Comfortable
208 tok/s 125–333 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	14.6 GB	Q8_0	Comfortable
166 tok/s 100–266 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	14.6 GB	Q8_0	Comfortable
159 tok/s 96–255 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	14.6 GB	Q8_0	Comfortable
159 tok/s 96–255 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	14.6 GB	Q8_0	Comfortable
152 tok/s 91–244 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	14.6 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	14.6 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	14.6 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	14.6 GB	Q8_0	Comfortable
131 tok/s 79–210 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	7.1 GB	Q3_K_M	Tight
128 tok/s 77–205 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
117 tok/s 70–188 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.6 GB	Q4_K_M	Tight
109 tok/s 66–175 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
109 tok/s 66–175 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	14.6 GB	Q8_0	Comfortable
83.4 tok/s 50–133 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	14.6 GB	Q8_0	Comfortable
83.4 tok/s 50–133 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	14.6 GB	Q8_0	Comfortable
69.5 tok/s 42–111 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	14.6 GB	Q8_0	Comfortable
68.0 tok/s 41–109 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	14.6 GB	Q8_0	Comfortable
67.5 tok/s 41–108 · low confidence	RTX A5000-8Q NVIDIA	8 GB	768 GB/s	Apr 2021	7.1 GB	Q3_K_M	Tight
66.5 tok/s 40–106 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	14.6 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: Cohere for AI,Brown University,Cohere,Carnegie Mellon University (CMU),Massachusetts Institute of Technology (MIT)
Organisation type: Industry,Academia,Industry,Academia,Academia
Country: Canada, United States of America
Published: 12 February 2024
Authors: Ahmet Üstün, Viraat Aryabumi, Zheng-Xin Yong, Wei-Yin Ko, Daniel D'souza, Gbemileke Onilude, Neel Bhandari, Shivalika Singh, Hui-Lee Ooi, Amr Kayid, Freddie Vargus, Phil Blunsom, Shayne Longpre, Niklas Muennighoff, Marzieh Fadaee, Julia Kreutzer, Sara Hooker

What it does

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

Domain: Language
Task: Language modeling/generation, Chat, Translation
Base model: mT5-XXL

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: 13B
Training data: 1,144,220,000,000 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.

Fine-tuning compute: 1.2 × 10²¹ FLOP

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 v4
Chips used: 128
Power draw: 86.2 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)
Training code: Unreleased

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: Speculative
Citations: 368

Sources

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

Reference: Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model
Last updated: 25 May 2026

The extremes

The ten fastest GPUs for Aya

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 Aya

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

Xeon Phi 5110P

Memory needed

7.1 GB

Fastest

261 tok/s

Aya is small enough at 13B parameters that hardware is rarely the obstacle — 509 of the cards we track can run it, including cards several years old.

At the low end, a Xeon Phi 5110P handles it — 8 GB, at Q3_K_M, for about 18.3 tokens per second.

At the other end, a B200 generates roughly 261 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Background

Aya was published by Cohere for AI,Brown University,Cohere,Carnegie Mellon University (CMU),Massachusetts Institute of Technology (MIT), in Canada, in February 2024. industry,Academia,Industry,Academia,Academia is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Chat, Translation.

It builds on mT5-XXL, which is why it shares that model's general shape and size.

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

Reading the throughput figures

Across every card that can run it, the middle of the range is about 21.2 tokens per second, and 459 of them clear the ten tokens per second that roughly matches reading speed.

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

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.

Training and provenance

The training set ran to roughly 1,144,220,000,000 tokens.

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

Step by step

How to choose a GPU for Aya

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

01

Start from the memory column

The table lists every card that can hold Aya — around 7.1 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
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 Aya 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 Aya — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Sort by speed to see how cards rank for Aya. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 261 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage Aya from those with room to spare. Buy for the second if the context might grow.
06

See what else that card runs

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

Answers

Aya — common questions

Where can I download Aya?

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

Can I run Aya if it does not fit in my GPU?

It can be split between the card and system memory, but Aya generates painfully slowly that way — the nearest miss we calculate is short by 3.2 GB. Nothing on this page assumes offloading.

Would two GPUs run Aya faster?

A second card roughly doubles the memory available but not the generation rate. With 509 cards already able to run Aya alone, the case for pairing is weak.

Why does the quantisation differ between cards for Aya?

Because capacity varies, so does how hard Aya has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Aya speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 156–417 tok/s on the B200 rather than a single number.

What GPU do I need to run Aya?

The smallest card in our catalogue that holds Aya is the Xeon Phi 5110P, with 8 GB of memory. It runs the model at Q3_K_M using about 7.1 GB, and produces roughly 18.3 tokens per second. 509 cards in total can run it.

How fast is Aya on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 261 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 459 of the cards that can run Aya clear that.

How much VRAM does Aya need?

About 7.1 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 Aya on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q3_K_M, using about 7.1 GB and generating roughly 131 tokens per second — a tight fit.

Can I run Aya on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q5_K_M, using about 10.1 GB and generating roughly 53.1 tokens per second — a tight fit.

Can I run Aya on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 11.6 GB and generating roughly 53.5 tokens per second — a comfortable fit.

Can I run Aya on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 14.6 GB and generating roughly 43.7 tokens per second — a comfortable fit.

Is Aya open source?

Its weights are published, so Aya 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 Aya have?

Aya has 13B parameters. 13B - fine tune of mT5 - from last page - model card. 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 Aya?

Aya was published by Cohere for AI,Brown University,Cohere,Carnegie Mellon University (CMU),Massachusetts Institute of Technology (MIT), based in Canada, categorised as industry,Academia,Industry,Academia,Academia.

When was Aya released?

Aya was published in February 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.

What is Aya used for?

Aya works in Language, and is recorded as handling language modeling/generation, Chat, Translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

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