Cohere Command A TPS calculator

Open weights Cohere 111B parameters March 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

43 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI200

64 GB · Q3_K_M · 13.2 tok/s

Fastest card

B200

30.5 tok/s · 180 GB

Which GPUs can run Cohere Command A?

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

43 cards match

Calculating

					Needs	Quantisation	Fit
30.5 tok/s 18–49 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	119.5 GB	Q8_0	Comfortable
30.5 tok/s 18–49 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	119.5 GB	Q8_0	Comfortable
29.6 tok/s 18–47 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	67.9 GB	Q4_K_M	Tight
29.6 tok/s 18–47 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	67.9 GB	Q4_K_M	Tight
28.3 tok/s 17–45 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	93.7 GB	Q6_K	Comfortable
26.9 tok/s 16–43 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	80.8 GB	Q5_K_M	Tight
24.4 tok/s 15–39 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	119.5 GB	Q8_0	Comfortable
24.4 tok/s 15–39 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	119.5 GB	Q8_0	Comfortable
23.0 tok/s 14–37 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	93.7 GB	Q6_K	Comfortable
22.9 tok/s 14–37 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	80.8 GB	Q5_K_M	Tight
22.9 tok/s 14–37 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	80.8 GB	Q5_K_M	Tight
22.9 tok/s 14–37 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	80.8 GB	Q5_K_M	Tight
20.8 tok/s 12–33 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	54.9 GB	Q3_K_M	Tight
18.7 tok/s 11–30 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	119.5 GB	Q8_0	Tight
18.7 tok/s 11–30 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	119.5 GB	Q8_0	Tight
18.0 tok/s 11–29 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	67.9 GB	Q4_K_M	Tight
18.0 tok/s 11–29 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	67.9 GB	Q4_K_M	Tight
18.0 tok/s 11–29 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	67.9 GB	Q4_K_M	Tight
18.0 tok/s 11–29 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	67.9 GB	Q4_K_M	Tight
18.0 tok/s 11–29 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	67.9 GB	Q4_K_M	Tight
18.0 tok/s 11–29 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	67.9 GB	Q4_K_M	Tight
17.9 tok/s 11–29 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	119.5 GB	Q8_0	Comfortable
17.1 tok/s 10–27 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	67.9 GB	Q4_K_M	Tight
17.1 tok/s 10–27 · low confidence	A800 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Nov 2022	67.9 GB	Q4_K_M	Tight
15.9 tok/s 10–25 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	119.5 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
Organisation type: Industry
Country: Canada
Published: 13 March 2025

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, Code generation, Question answering

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: 111B
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 (non-commercial)
Training code: Unreleased
Hugging Face: CohereLabs

How it is classified

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

Likely above 10²³ FLOP: Yes
Record confidence: Confident

Sources

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

Reference: Introducing Command A: Max performance, minimal compute
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Cohere Command A

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 Cohere Command A

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

Radeon Instinct MI200

Memory needed

54.9 GB

Fastest

30.5 tok/s

Cohere Command A reaches a parameter count of 111B. That puts it above consumer hardware, into the range where a card is bought for this purpose rather than repurposed for it. The number of cards we track that can hold it: 43.

The smallest card that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB, running it at a compression of Q3_K_M and producing around 13.2 tokens per second.

Top of the range is B200, generating roughly 30.5 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

Cohere Command A was published by Cohere, in the country recorded as Canada, during March 2025. The category the publisher falls under is industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Chat, Code generation, Question answering.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. On Hugging Face it is published under the organisation CohereLabs.

How fast it runs, and why

Half the cards that hold it manage more than 17.9 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 39 of them.

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.

Step by step

How to choose a GPU for Cohere Command A

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 able to hold Cohere Command A, needing around 54.9 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 Cohere Command A.
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

Sort by speed

Ranking by tokens per second follows memory bandwidth rather than core counts, for Cohere Command A. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 30.5 tok/s.
05

Read the fit column last

The fit column separates cards that just manage it from those with room to spare, in the case of Cohere Command A. 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

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond Cohere Command A.

Answers

Cohere Command A — common questions

Cohere Command A— how much VRAM does it need?

It needs about 54.9 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.

Cohere Command A— 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.

Cohere Command A— how many parameters does it have?

It has a parameter count of 111B. a 111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI. 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.

Cohere Command A— who created it?

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

Cohere Command A— when was it released?

It was published in March 2025.

Cohere Command A— what is it used for?

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

Cohere Command A— where can I download it?

Its weights are published on Hugging Face, under the organisation CohereLabs. We do not host model files — this site calculates what hardware is needed to run them.

Cohere Command A— 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 24.7 GB. Every figure here assumes the whole model is resident on the card.

Cohere Command A— 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: 43. So a second card is rarely the answer here.

Cohere Command A— 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: 6. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Cohere Command A— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 18–49 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Cohere Command A— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB. It runs the model at a compression of Q3_K_M using about 54.9 GB, and produces roughly 13.2 tokens per second. The number of cards able to run it in total: 43.

Cohere Command A— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 30.5 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: 39.

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