Mistral NeMo TPS calculator

Open weights Mistral AI 12B 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

509 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 5110P

8 GB · Q3_K_M · 19.8 tok/s

Fastest card

B200

282 tok/s · 180 GB

Which GPUs can run Mistral NeMo?

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
282 tok/s 240–339	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	14.0 GB	Q8_0	Comfortable
282 tok/s 240–339	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	14.0 GB	Q8_0	Comfortable
225 tok/s 135–361 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	14.0 GB	Q8_0	Comfortable
225 tok/s 135–361 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	14.0 GB	Q8_0	Comfortable
180 tok/s 108–289 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	14.0 GB	Q8_0	Comfortable
173 tok/s 147–207	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	14.0 GB	Q8_0	Comfortable
173 tok/s 147–207	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	14.0 GB	Q8_0	Comfortable
165 tok/s 99–264 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	14.0 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	14.0 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	14.0 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	14.0 GB	Q8_0	Comfortable
142 tok/s 121–170	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	7.1 GB	Q3_K_M	Tight
139 tok/s 118–167	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	14.0 GB	Q8_0	Comfortable
127 tok/s 108–153	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.5 GB	Q4_K_M	Tight
119 tok/s 101–142	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	14.0 GB	Q8_0	Comfortable
119 tok/s 101–142	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	14.0 GB	Q8_0	Comfortable
119 tok/s 101–142	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	14.0 GB	Q8_0	Comfortable
119 tok/s 101–142	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	14.0 GB	Q8_0	Comfortable
119 tok/s 101–142	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	14.0 GB	Q8_0	Comfortable
90.3 tok/s 54–144 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	14.0 GB	Q8_0	Comfortable
90.3 tok/s 54–144 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	14.0 GB	Q8_0	Comfortable
75.3 tok/s 45–120 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	14.0 GB	Q8_0	Comfortable
73.6 tok/s 44–118 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	14.0 GB	Q8_0	Comfortable
73.1 tok/s 62–88	RTX A5000-8Q NVIDIA	8 GB	768 GB/s	Apr 2021	7.1 GB	Q3_K_M	Tight
72.0 tok/s 61–86	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	14.0 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: 18 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: Language modeling/generation, Code generation
Approach: Self-supervised learning

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: 12B
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: 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: Mistral NeMo
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Mistral NeMo

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 Mistral NeMo

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

282 tok/s

Mistral NeMo is small enough at 12B 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 19.8 tokens per second.

At the other end, a B200 generates roughly 282 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Where it came from

Mistral NeMo was published by Mistral AI, in France, in July 2024. It comes out of industry.

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

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

Understanding the speeds

Half the cards that hold it manage more than 21.2 tokens per second, and 455 exceed reading speed outright.

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

Its attention layout is on file, so the memory figures are computed exactly rather than approximated.

Step by step

How to choose a GPU for Mistral NeMo

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

Every card here has been checked against Mistral NeMo — around 7.1 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

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

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of Mistral NeMo — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Rank by throughput rather than spec sheet

The speed ordering for Mistral NeMo is effectively an ordering by memory bandwidth, which is why the B200 tops it at 282 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage Mistral NeMo 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 Mistral NeMo.

Answers

Mistral NeMo — common questions

Can I run Mistral NeMo on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 14.0 GB and generating roughly 39.9 tokens per second — a tight fit.

Can I run Mistral NeMo on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 14.0 GB and generating roughly 47.3 tokens per second — a comfortable fit.

Is Mistral NeMo open source?

Its weights are published, so Mistral NeMo 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 Mistral NeMo have?

Mistral NeMo has 12B parameters. 12b. 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 Mistral NeMo?

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

When was Mistral NeMo released?

Mistral NeMo 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 Mistral NeMo used for?

Mistral NeMo works in Language, and is recorded as handling language modeling/generation, Code generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Mistral NeMo?

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 Mistral NeMo 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 3.1 GB. Our figures for Mistral NeMo assume it is fully resident.

Would two GPUs run Mistral NeMo faster?

Capacity adds across cards; throughput does not. Since 509 of the cards we track already hold Mistral NeMo on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Mistral NeMo?

Each card is shown running the least-compressed copy it can hold, and Mistral NeMo appears at 4 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Mistral NeMo speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 240–339 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 Mistral NeMo?

The smallest card in our catalogue that holds Mistral NeMo 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 19.8 tokens per second. 509 cards in total can run it.

How fast is Mistral NeMo on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 282 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 455 of the cards that can run Mistral NeMo clear that.

How much VRAM does Mistral NeMo 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 Mistral NeMo 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 142 tokens per second — a tight fit.

Can I run Mistral NeMo on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q5_K_M, using about 9.9 GB and generating roughly 57.5 tokens per second — a tight fit.

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