Command A+ TPS calculator

Open weights Cohere,Cohere Labs (formerly Cohere for AI) 218B parameters May 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

17 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI250

128 GB · IQ4_XS · 67.8 tok/s

Fastest card

B200

154 tok/s · 180 GB

Which GPUs can run 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

17 cards match

Calculating

					Needs	Quantisation	Fit
154 tok/s 93–247 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	147.0 GB	Q5_K_M	Tight
135 tok/s 81–217 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	108.9 GB	IQ4_XS	Tight
122 tok/s 73–195 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	121.6 GB	Q4_K_M	Tight
122 tok/s 73–195 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	121.6 GB	Q4_K_M	Tight
110 tok/s 66–176 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	108.9 GB	IQ4_XS	Tight
86.4 tok/s 52–138 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	223.1 GB	Q8_0	Tight
69.0 tok/s 41–110 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	223.1 GB	Q8_0	Tight
69.0 tok/s 41–110 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	223.1 GB	Q8_0	Tight
67.8 tok/s 41–108 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	108.9 GB	IQ4_XS	Tight
67.8 tok/s 41–108 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	108.9 GB	IQ4_XS	Tight
65.1 tok/s 39–104 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	172.4 GB	Q6_K	Tight
65.1 tok/s 39–104 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	172.4 GB	Q6_K	Tight
56.5 tok/s 34–90 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	108.9 GB	IQ4_XS	Tight
55.3 tok/s 33–88 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	108.9 GB	IQ4_XS	Tight
50.5 tok/s 30–81 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	223.1 GB	Q8_0	Tight
7.2 tok/s 4–12 · low confidence	GB10 NVIDIA	128 GB	273 GB/s	Oct 2025	108.9 GB	IQ4_XS	Tight
7.2 tok/s 4–12 · low confidence	Jetson T5000 NVIDIA	128 GB	273 GB/s	Aug 2025	108.9 GB	IQ4_XS	Tight

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,Cohere Labs (formerly Cohere for AI)
Organisation type: Industry,Industry
Country: Canada
Published: 20 May 2026

What it does

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

Domain: Language, Multimodal, Vision
Task: Language modeling/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: 218B
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)
Hugging Face: CohereLabs

How it is classified

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

Record confidence: Confident

Sources

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

Reference: Introducing Command A+: Making sovereign agentic capabilities available to all
Last updated: 11 August 2026

The extremes

The ten fastest GPUs that run 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 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

The hardware side

Minimum card

Radeon Instinct MI250

Memory needed

108.9 GB

Fastest

154 tok/s

Command A+ reaches a parameter count of 218B. That is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job, and every card able to hold it alone is a datacentre part. The number that can: 17.

At the low end it is handled by Radeon Instinct MI250, with a memory capacity of 128 GB, running it at a compression of IQ4_XS and producing around 67.8 tokens per second.

Top of the range is B200, generating roughly 154 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

Command A+ was published by Cohere,Cohere Labs (formerly Cohere for AI), in the country recorded as Canada, during May 2026. It comes out of an organisation categorised as industry,Industry.

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

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. On Hugging Face it is published under the organisation CohereLabs.

What decides the speed

Across every card that can run it, the middle of the range sits at 67.8 tokens per second. Producing text faster than most people read it: 15 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.

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.

Step by step

How to choose a GPU for 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

Check what it needs before anything else

Every card here has been checked against Command A+, needing around 108.9 GB at a compression of IQ4_XS. That figure, not the headline performance of a card, is what decides whether it runs.
02

Decide how long your conversations run

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting Command A+.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of IQ4_XS 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

Ranking by tokens per second follows memory bandwidth rather than core counts, for Command A+. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 154 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 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

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 Command A+.

Answers

Command A+ — common questions

Command A+— how much VRAM does it need?

It needs about 108.9 GB at a compression of IQ4_XS, 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.

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.

Command A+— how many parameters does it have?

It has a parameter count of 218B. "218B total; 25B active". 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.

Command A+— who created it?

It was published by Cohere,Cohere Labs (formerly Cohere for AI), based in Canada, an organisation categorised as industry,Industry.

Command A+— when was it released?

It was published in May 2026.

Command A+— what is it used for?

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

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.

Command A+— 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. The nearest miss we calculate falls short by 35.2 GB. Every figure here assumes the whole model is resident on the card.

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: 17. So a second card is rarely the answer here.

Command A+— why does the quantisation differ between cards?

Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

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: 93–247 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

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

The smallest card in our catalogue that holds it is Radeon Instinct MI250, with a memory capacity of 128 GB. It runs the model at a compression of IQ4_XS using about 108.9 GB, and produces roughly 67.8 tokens per second. The number of cards able to run it in total: 17.

Command A+— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 154 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: 15.

Source

Original publication

Record last updated 11 August 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