Magistral Small 1.2 TPS calculator

Open weights Mistral AI 24B parameters September 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

241 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 7120P

16 GB · IQ4_XS · 9.9 tok/s

Fastest card

B200

141 tok/s · 180 GB

Which GPUs can run Magistral Small 1.2?

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
141 tok/s 85–226 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	26.4 GB	Q8_0	Comfortable
141 tok/s 85–226 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	26.4 GB	Q8_0	Comfortable
113 tok/s 68–180 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	26.4 GB	Q8_0	Comfortable
113 tok/s 68–180 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	26.4 GB	Q8_0	Comfortable
90.2 tok/s 54–144 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	26.4 GB	Q8_0	Comfortable
86.3 tok/s 52–138 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	26.4 GB	Q8_0	Comfortable
86.3 tok/s 52–138 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	26.4 GB	Q8_0	Comfortable
82.6 tok/s 50–132 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	26.4 GB	Q8_0	Comfortable
73.3 tok/s 44–117 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	26.4 GB	Q8_0	Comfortable
73.3 tok/s 44–117 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	26.4 GB	Q8_0	Comfortable
73.3 tok/s 44–117 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	26.4 GB	Q8_0	Comfortable
69.5 tok/s 42–111 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	26.4 GB	Q8_0	Comfortable
59.3 tok/s 36–95 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	26.4 GB	Q8_0	Comfortable
59.3 tok/s 36–95 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	26.4 GB	Q8_0	Comfortable
59.3 tok/s 36–95 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	26.4 GB	Q8_0	Comfortable
59.3 tok/s 36–95 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	26.4 GB	Q8_0	Comfortable
59.3 tok/s 36–95 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	26.4 GB	Q8_0	Comfortable
49.0 tok/s 29–78 · low confidence	Tesla V100 SXM2 16 GB NVIDIA	16 GB	1,130 GB/s	Nov 2019	13.8 GB	IQ4_XS	Tight
45.2 tok/s 27–72 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	26.4 GB	Q8_0	Comfortable
45.2 tok/s 27–72 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	26.4 GB	Q8_0	Comfortable
41.6 tok/s 25–67 · low confidence	GeForce RTX 5080 NVIDIA	16 GB	960 GB/s	Jan 2025	13.8 GB	IQ4_XS	Tight
38.9 tok/s 23–62 · low confidence	Tesla V100 DGXS 16 GB NVIDIA	16 GB	897 GB/s	Mar 2018	13.8 GB	IQ4_XS	Tight
38.9 tok/s 23–62 · low confidence	Tesla V100 PCIe 16 GB NVIDIA	16 GB	897 GB/s	Jun 2017	13.8 GB	IQ4_XS	Tight
38.9 tok/s 23–62 · low confidence	Tesla V100 SXM2 16 GB NVIDIA	16 GB	897 GB/s	Jun 2017	13.8 GB	IQ4_XS	Tight
38.8 tok/s 23–62 · low confidence	GeForce RTX 5070 Ti NVIDIA	16 GB	896 GB/s	Feb 2025	13.8 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: Mistral AI
Organisation type: Industry
Country: France
Published: 18 September 2025

What it does

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

Domain: Language, Vision, Multimodal
Task: Language modeling/generation, Question answering, Quantitative reasoning, Code generation, Translation, Visual question answering, Image captioning
Base model: Mistral Small 3.2

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: 24B
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: Introducing Magistral Small 1.2 & Magistral Medium 1.2, minor updates to our Magistral 1.1 models!
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Magistral Small 1.2

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 Magistral Small 1.2

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

Xeon Phi 7120P

Memory needed

13.8 GB

Fastest

141 tok/s

With 24B parameters, Magistral Small 1.2 lands in the range a serious desktop card can handle once the weights are compressed. 241 of the cards we track can run it.

The smallest card that holds it is the Xeon Phi 7120P with 16 GB, running it at IQ4_XS and producing around 9.9 tokens per second.

A B200 is the fastest we calculate for it: about 141 tokens per second, from 8,000 GB/s of memory bandwidth.

About this model

Magistral Small 1.2 was published by Mistral AI, in France, in September 2025. It comes out of industry.

It works in Language, Vision, Multimodal, and is recorded as doing language modeling/generation, Question answering, Quantitative reasoning, Code generation, Translation, Visual question answering, Image captioning.

Its starting point was Mistral Small 3.2 — most models at this scale are adapted from an existing base rather than built from nothing.

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.

How fast it runs, and why

The median result is around 19.4 tokens per second; 193 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.

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 Magistral Small 1.2

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 Magistral Small 1.2 — around 13.8 GB at IQ4_XS. 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: at long context Magistral Small 1.2 can slip off a card that handles short questions easily.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of Magistral Small 1.2 — IQ4_XS on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for Magistral Small 1.2 follows memory bandwidth, not core counts, which is why the B200 tops it at 141 tok/s.
05

Look at the headroom, not just the fit

Tight means Magistral Small 1.2 loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
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. Worth a look before buying for Magistral Small 1.2 alone — a card is usually bought for more than one model.

Answers

Magistral Small 1.2 — common questions

Would two GPUs run Magistral Small 1.2 faster?

Capacity adds across cards; throughput does not. Since 241 of the cards we track already hold Magistral Small 1.2 on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Magistral Small 1.2?

A larger card holds a more accurate copy. Across the cards that run Magistral Small 1.2, 4 compression levels are used; the floor control above pins it to one.

How accurate are these Magistral Small 1.2 speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 85–226 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 Magistral Small 1.2?

The smallest card in our catalogue that holds Magistral Small 1.2 is the Xeon Phi 7120P, with 16 GB of memory. It runs the model at IQ4_XS using about 13.8 GB, and produces roughly 9.9 tokens per second. 241 cards in total can run it.

How fast is Magistral Small 1.2 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 141 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 193 of the cards that can run Magistral Small 1.2 clear that.

How much VRAM does Magistral Small 1.2 need?

About 13.8 GB at IQ4_XS 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 Magistral Small 1.2 on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at IQ4_XS, using about 13.8 GB and generating roughly 49.0 tokens per second — a tight fit.

Can I run Magistral Small 1.2 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q6_K, using about 20.8 GB and generating roughly 34.4 tokens per second — a tight fit.

Is Magistral Small 1.2 open source?

Its weights are published, so Magistral Small 1.2 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 Magistral Small 1.2 have?

Magistral Small 1.2 has 24B parameters. 24B. 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 Magistral Small 1.2?

Magistral Small 1.2 was published by Mistral AI, based in France, categorised as industry.

When was Magistral Small 1.2 released?

Magistral Small 1.2 was published in September 2025.

What is Magistral Small 1.2 used for?

Magistral Small 1.2 works in Language, Vision, Multimodal, and is recorded as handling language modeling/generation, Question answering, Quantitative reasoning, Code generation, Translation, Visual question answering, Image captioning. 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.

Where can I download Magistral Small 1.2?

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 Magistral Small 1.2 if it does not fit in my GPU?

It can be split between the card and system memory, but Magistral Small 1.2 generates painfully slowly that way — the nearest miss we calculate is short by 4.4 GB. Nothing on this page assumes offloading.

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