Codestral Mamba TPS calculator

Open weights Mistral AI 7.3B parameters July 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

589 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla K20c

5 GB · Q3_K_M · 27.7 tok/s

Fastest card

B200

465 tok/s · 180 GB

Which GPUs can run Codestral Mamba?

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

589 cards match

Calculating

					Needs	Quantisation	Fit
465 tok/s 279–744 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	8.5 GB	Q8_0	Comfortable
465 tok/s 279–744 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	8.5 GB	Q8_0	Comfortable
371 tok/s 223–594 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	8.5 GB	Q8_0	Comfortable
371 tok/s 223–594 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	8.5 GB	Q8_0	Comfortable
297 tok/s 178–475 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	8.5 GB	Q8_0	Comfortable
284 tok/s 171–455 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.5 GB	Q8_0	Comfortable
284 tok/s 171–455 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.5 GB	Q8_0	Comfortable
272 tok/s 163–435 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	8.5 GB	Q8_0	Comfortable
241 tok/s 145–386 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	8.5 GB	Q8_0	Comfortable
241 tok/s 145–386 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	8.5 GB	Q8_0	Comfortable
241 tok/s 145–386 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	8.5 GB	Q8_0	Comfortable
229 tok/s 137–366 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	8.5 GB	Q8_0	Comfortable
195 tok/s 117–313 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.5 GB	Q8_0	Comfortable
195 tok/s 117–313 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	8.5 GB	Q8_0	Comfortable
195 tok/s 117–313 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	8.5 GB	Q8_0	Comfortable
195 tok/s 117–313 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.5 GB	Q8_0	Comfortable
195 tok/s 117–313 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	8.5 GB	Q8_0	Comfortable
149 tok/s 89–238 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	8.5 GB	Q8_0	Comfortable
149 tok/s 89–238 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	8.5 GB	Q8_0	Comfortable
126 tok/s 76–201 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.8 GB	Q6_K	Tight
124 tok/s 74–198 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	8.5 GB	Q8_0	Comfortable
121 tok/s 73–194 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	8.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	8.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	8.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	8.5 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: Mistral AI
Organisation type: Industry
Country: France
Published: 16 July 2024
Authors: Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Alok Kothari, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Augustin Garreau, Austin Birky, Bam4d, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Carole Rambaud, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gaspard Blanchet, Gianna Lengyel, Guillaume Bour, Guillaume …

What it does

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

Domain: Language
Task: Code generation, Code autocompletion

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: 7.3B
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)
Training code: Unreleased
Hugging Face: mistralai

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: As a tribute to Cleopatra, whose glorious destiny ended in tragic snake circumstances, we are proud to release Codestral Mamba, a Mamba2 language model specialised in code generation, available under an Apache 2.0 license.
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Codestral Mamba

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 Codestral Mamba

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

Tesla K20c

Memory needed

4.3 GB

Fastest

465 tok/s

Codestral Mamba is small enough at 7.3B parameters that hardware is rarely the obstacle — 589 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the Tesla K20c with 5 GB, running it at Q3_K_M and producing around 27.7 tokens per second.

Top of the range is the B200, at roughly 465 tokens per second thanks to 8,000 GB/s of bandwidth.

About this model

Codestral Mamba was published by Mistral AI, in France, in July 2024. The organisation is categorised as industry.

It works in Language, and is recorded as doing code generation, Code autocompletion.

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 mistralai organisation on Hugging Face.

How fast it runs, and why

The median result is around 25.1 tokens per second; 559 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.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

Step by step

How to choose a GPU for Codestral Mamba

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 Codestral Mamba — around 4.3 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

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

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage Codestral Mamba by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for Codestral Mamba follows memory bandwidth, not core counts, which is why the B200 tops it at 465 tok/s.
05

Read the fit column last

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

Open the card you have settled on

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Codestral Mamba.

Answers

Codestral Mamba — common questions

How many parameters does Codestral Mamba have?

Codestral Mamba has 7.3B parameters. "This is an instructed model, with 7,285,403,648 parameters.". 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 Codestral Mamba?

Codestral Mamba was published by Mistral AI, based in France, categorised as industry.

When was Codestral Mamba released?

Codestral Mamba was published in July 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 Codestral Mamba used for?

Codestral Mamba works in Language, and is recorded as handling code generation, Code autocompletion. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Codestral Mamba?

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

Can I run Codestral Mamba 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 — the nearest miss we calculate is short by 1.5 GB. Our figures for Codestral Mamba assume it is fully resident.

Would two GPUs run Codestral Mamba faster?

Capacity adds across cards; throughput does not. Since 589 of the cards we track already hold Codestral Mamba on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Codestral Mamba?

A larger card holds a more accurate copy. Across the cards that run Codestral Mamba, 4 compression levels are used; the floor control above pins it to one.

How accurate are these Codestral Mamba speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 279–744 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 Codestral Mamba?

The smallest card in our catalogue that holds Codestral Mamba is the Tesla K20c, with 5 GB of memory. It runs the model at Q3_K_M using about 4.3 GB, and produces roughly 27.7 tokens per second. 589 cards in total can run it.

How fast is Codestral Mamba on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 465 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 559 of the cards that can run Codestral Mamba clear that.

How much VRAM does Codestral Mamba need?

About 4.3 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 Codestral Mamba on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q6_K, using about 6.8 GB and generating roughly 126 tokens per second — a tight fit.

Can I run Codestral Mamba on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 8.5 GB and generating roughly 53.0 tokens per second — a comfortable fit.

Can I run Codestral Mamba on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 8.5 GB and generating roughly 65.7 tokens per second — a comfortable fit.

Can I run Codestral Mamba on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 8.5 GB and generating roughly 77.9 tokens per second — a comfortable fit.

Is Codestral Mamba open source?

Its weights are published, so Codestral Mamba 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.

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