Aya Expanse 32B TPS calculator

Open weights Cohere for AI 32.3B parameters October 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 · Q3_K_M · 22.6 tok/s

Fastest card

B200

105 tok/s · 180 GB

Which GPUs can run Aya Expanse 32B?

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
105 tok/s 63–168 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	35.3 GB	Q8_0	Comfortable
105 tok/s 63–168 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	35.3 GB	Q8_0	Comfortable
83.8 tok/s 50–134 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	35.3 GB	Q8_0	Comfortable
83.8 tok/s 50–134 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	35.3 GB	Q8_0	Comfortable
67.0 tok/s 40–107 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	35.3 GB	Q8_0	Comfortable
64.1 tok/s 38–103 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	35.3 GB	Q8_0	Comfortable
64.1 tok/s 38–103 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	35.3 GB	Q8_0	Comfortable
61.4 tok/s 37–98 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	35.3 GB	Q8_0	Comfortable
54.5 tok/s 33–87 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	35.3 GB	Q8_0	Comfortable
54.5 tok/s 33–87 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	35.3 GB	Q8_0	Comfortable
54.5 tok/s 33–87 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	35.3 GB	Q8_0	Comfortable
51.7 tok/s 31–83 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	35.3 GB	Q8_0	Comfortable
44.1 tok/s 26–70 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	35.3 GB	Q8_0	Comfortable
44.1 tok/s 26–70 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	35.3 GB	Q8_0	Comfortable
44.1 tok/s 26–70 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	35.3 GB	Q8_0	Comfortable
44.1 tok/s 26–70 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	35.3 GB	Q8_0	Comfortable
44.1 tok/s 26–70 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	35.3 GB	Q8_0	Comfortable
40.6 tok/s 24–65 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	20.2 GB	Q4_K_M	Tight
36.9 tok/s 22–59 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	20.2 GB	Q4_K_M	Tight
35.6 tok/s 21–57 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	27.8 GB	Q6_K	Tight
35.6 tok/s 21–57 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	27.8 GB	Q6_K	Tight
34.1 tok/s 20–55 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	27.8 GB	Q6_K	Tight
34.1 tok/s 20–55 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	27.8 GB	Q6_K	Tight
33.6 tok/s 20–54 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	35.3 GB	Q8_0	Comfortable
33.6 tok/s 20–54 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	35.3 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
Organisation type: Industry
Country: Canada
Published: 24 October 2024

What it does

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

Domain: Language
Task: Language modeling/generation, Translation

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: 32.3B
Training data: 34,513,333,333 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: 6.7 × 10²¹ FLOP
How it was established: Operation counting

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

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: Cohere For AI launches Aya Expanse, a state-of-the-art multilingual family of models to help close the language gap with AI.
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Aya Expanse 32B

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 Expanse 32B

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

16.5 GB

Fastest

105 tok/s

Aya Expanse 32B reaches a parameter count of 32.3B. 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 Q3_K_M and producing around 22.6 tokens per second.

Top of the range is B200, generating roughly 105 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

Aya Expanse 32B was published by Cohere for AI, in the country recorded as Canada, during October 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, Translation.

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.

How fast it runs, and why

Half the cards that hold it manage more than 20.5 tokens per second. Producing text faster than most people read it: 102 of them.

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.

How it was trained

The training run consumed about 6.7 × 10²¹ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 34,513,333,333 tokens of text.

Step by step

How to choose a GPU for Aya Expanse 32B

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

Start from what it actually needs, which is the requirement of Aya Expanse 32B, needing around 16.5 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
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, because at long context a card that handles short questions easily can be dropped by Aya Expanse 32B.
03

Decide how much compression you will accept

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

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for Aya Expanse 32B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 105 tok/s.
05

Check the fit verdict before buying

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Aya Expanse 32B. 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 Aya Expanse 32B.

Answers

Aya Expanse 32B — common questions

Aya Expanse 32B— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 63–168 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Aya Expanse 32B— 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 Q3_K_M using about 16.5 GB, and produces roughly 22.6 tokens per second. The number of cards able to run it in total: 132.

Aya Expanse 32B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 105 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: 102.

Aya Expanse 32B— how much VRAM does it need?

It needs about 16.5 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.

Aya Expanse 32B— 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 Q4_K_M, using about 20.2 GB and generating roughly 40.6 tokens per second. The fit is tight.

Aya Expanse 32B— 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.

Aya Expanse 32B— how many parameters does it have?

It has a parameter count of 32.3B. 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.

Aya Expanse 32B— who created it?

It was published by Cohere for AI, based in Canada, an organisation categorised as industry.

Aya Expanse 32B— when was it released?

It was published in October 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.

Aya Expanse 32B— what is it used for?

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

Aya Expanse 32B— 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.

Aya Expanse 32B— how much compute was used to train it?

Training consumed around 6.7 × 10²¹ FLOP. 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.

Aya Expanse 32B— 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 5.8 GB. Every figure here assumes the whole model is resident on the card.

Aya Expanse 32B— 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: 132. So a second card is rarely the answer here.

Aya Expanse 32B— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

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