Mistral Small v24.09 TPS calculator

Open weights Mistral AI 22B parameters September 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

241 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 7120P

16 GB · Q4_K_M · 10.2 tok/s

Fastest card

B200

154 tok/s · 180 GB

Which GPUs can run Mistral Small v24.09?

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

241 cards match

Calculating

					Needs	Quantisation	Fit
154 tok/s 131–185	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	24.6 GB	Q8_0	Comfortable
154 tok/s 131–185	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	24.6 GB	Q8_0	Comfortable
123 tok/s 74–197 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	24.6 GB	Q8_0	Comfortable
123 tok/s 74–197 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	24.6 GB	Q8_0	Comfortable
98.4 tok/s 59–157 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	24.6 GB	Q8_0	Comfortable
94.1 tok/s 80–113	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	24.6 GB	Q8_0	Comfortable
94.1 tok/s 80–113	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	24.6 GB	Q8_0	Comfortable
90.1 tok/s 54–144 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	24.6 GB	Q8_0	Comfortable
80.0 tok/s 48–128 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	24.6 GB	Q8_0	Comfortable
80.0 tok/s 48–128 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	24.6 GB	Q8_0	Comfortable
80.0 tok/s 48–128 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	24.6 GB	Q8_0	Comfortable
75.9 tok/s 64–91	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	24.6 GB	Q8_0	Comfortable
64.7 tok/s 55–78	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	24.6 GB	Q8_0	Comfortable
64.7 tok/s 55–78	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	24.6 GB	Q8_0	Comfortable
64.7 tok/s 55–78	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	24.6 GB	Q8_0	Comfortable
64.7 tok/s 55–78	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	24.6 GB	Q8_0	Comfortable
64.7 tok/s 55–78	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	24.6 GB	Q8_0	Comfortable
50.2 tok/s 43–60	Tesla V100 SXM2 16 GB NVIDIA	16 GB	1,130 GB/s	Nov 2019	14.4 GB	Q4_K_M	Tight
49.3 tok/s 30–79 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	24.6 GB	Q8_0	Comfortable
49.3 tok/s 30–79 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	24.6 GB	Q8_0	Comfortable
42.7 tok/s 36–51	GeForce RTX 5080 NVIDIA	16 GB	960 GB/s	Jan 2025	14.4 GB	Q4_K_M	Tight
41.0 tok/s 25–66 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	24.6 GB	Q8_0	Comfortable
40.2 tok/s 24–64 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	24.6 GB	Q8_0	Comfortable
39.9 tok/s 34–48	Tesla V100 DGXS 16 GB NVIDIA	16 GB	897 GB/s	Mar 2018	14.4 GB	Q4_K_M	Tight
39.9 tok/s 34–48	Tesla V100 PCIe 16 GB NVIDIA	16 GB	897 GB/s	Jun 2017	14.4 GB	Q4_K_M	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: Mistral AI
Organisation type: Industry
Country: France
Published: 17 September 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, Diogo Costa, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gaspard Blanchet, Gianna Lengyel, Guillaume Bou…

What it does

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

Domain: Language
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: 22B
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: 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: AI in abundance
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Mistral Small v24.09

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 Small v24.09

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

Hardware requirements in practice

Minimum card

Xeon Phi 7120P

Memory needed

14.4 GB

Fastest

154 tok/s

Mistral Small v24.09 reaches a parameter count of 22B. 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: 241.

The entry point is Xeon Phi 7120P, with a memory capacity of 16 GB, running it at a compression of Q4_K_M and producing around 10.2 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

Mistral Small v24.09 was published by Mistral AI, in the country recorded as France, during September 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, Question answering.

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. On Hugging Face it is published under the organisation mistralai.

What decides the speed

Half the cards that hold it manage more than 19.9 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 194 of them.

It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.

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 Small v24.09

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 Mistral Small v24.09, needing around 14.4 GB at a compression of Q4_K_M. Capacity is the gate — a card either holds it or it does not.
02

Set the context length you will work at

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 Mistral Small v24.09.
03

Set a quality floor

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of Q4_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

Compare tokens per second, not specifications

Ranking by tokens per second follows memory bandwidth rather than core counts, for Mistral Small v24.09. 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 Mistral Small v24.09. 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

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 Mistral Small v24.09.

Answers

Mistral Small v24.09 — common questions

Mistral Small v24.09— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Question answering. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Mistral Small v24.09— where can I download it?

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

Mistral Small v24.09— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 3.6 GB. Every figure here assumes the whole model is resident on the card.

Mistral Small v24.09— would two GPUs run it faster?

A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 241. So a second card is rarely the answer here.

Mistral Small v24.09— why does the quantisation differ between cards?

A larger card holds a more accurate copy. The number of compression levels used across the cards that run it: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Mistral Small v24.09— how accurate are these speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked, which is why each is published as a range rather than a single number. One example: 131–185 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Mistral Small v24.09— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Xeon Phi 7120P, with a memory capacity of 16 GB. It runs the model at a compression of Q4_K_M using about 14.4 GB, and produces roughly 10.2 tokens per second. The number of cards able to run it in total: 241.

Mistral Small v24.09— 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: 194.

Mistral Small v24.09— how much VRAM does it need?

It needs about 14.4 GB at a compression of Q4_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.

Mistral Small v24.09— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q4_K_M, using about 14.4 GB and generating roughly 50.2 tokens per second. The fit is tight.

Mistral Small v24.09— 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 Q6_K, using about 19.5 GB and generating roughly 37.5 tokens per second. The fit is tight.

Mistral Small v24.09— 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.

Mistral Small v24.09— how many parameters does it have?

It has a parameter count of 22B. 22B. 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.

Mistral Small v24.09— who created it?

It was published by Mistral AI, based in France, an organisation categorised as industry.

Mistral Small v24.09— when was it released?

It was published in September 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.

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