Mistral Medium 3.5 TPS calculator

Open weights Mistral AI 128B parameters April 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

38 of 818 cards that can run it

Smallest card that fits

RTX PRO 5000 72 GB Blackwell

72 GB · Q3_K_M · 12.0 tok/s

Fastest card

H100 NVL 94 GB

30.1 tok/s · 94 GB

Which GPUs can run Mistral Medium 3.5?

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

38 cards match

Calculating

					Needs	Quantisation	Fit
30.1 tok/s 18–48 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	78.1 GB	Q4_K_M	Tight
27.3 tok/s 16–44 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	70.7 GB	IQ4_XS	Tight
27.3 tok/s 16–44 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	70.7 GB	IQ4_XS	Tight
26.5 tok/s 16–42 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	137.7 GB	Q8_0	Tight
26.5 tok/s 16–42 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	137.7 GB	Q8_0	Comfortable
25.7 tok/s 15–41 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	78.1 GB	Q4_K_M	Tight
25.7 tok/s 15–41 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	78.1 GB	Q4_K_M	Tight
25.7 tok/s 15–41 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	78.1 GB	Q4_K_M	Tight
24.6 tok/s 15–39 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	107.9 GB	Q6_K	Tight
23.5 tok/s 14–38 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	107.9 GB	Q6_K	Tight
23.5 tok/s 14–38 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	107.9 GB	Q6_K	Tight
21.1 tok/s 13–34 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	137.7 GB	Q8_0	Comfortable
21.1 tok/s 13–34 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	137.7 GB	Q8_0	Comfortable
20.0 tok/s 12–32 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	107.9 GB	Q6_K	Tight
16.6 tok/s 10–27 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	70.7 GB	IQ4_XS	Tight
16.6 tok/s 10–27 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	70.7 GB	IQ4_XS	Tight
16.6 tok/s 10–27 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	70.7 GB	IQ4_XS	Tight
16.6 tok/s 10–27 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	70.7 GB	IQ4_XS	Tight
16.6 tok/s 10–27 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	70.7 GB	IQ4_XS	Tight
16.6 tok/s 10–27 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	70.7 GB	IQ4_XS	Tight
15.8 tok/s 9–25 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	70.7 GB	IQ4_XS	Tight
15.8 tok/s 9–25 · low confidence	A800 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Nov 2022	70.7 GB	IQ4_XS	Tight
15.5 tok/s 9–25 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	137.7 GB	Q8_0	Comfortable
13.7 tok/s 8–22 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	137.7 GB	Q8_0	Comfortable
13.7 tok/s 8–22 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	137.7 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: 29 April 2026

What it does

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

Domain: Language, Multimodal
Task: Question answering, Language modeling/generation

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: 128B
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 (restricted use)

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 Medium 3.5 128B
Last updated: 27 May 2026

The extremes

The ten fastest GPUs for Mistral Medium 3.5

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 Medium 3.5

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 you need to run it

Minimum card

RTX PRO 5000 72 GB Blackwell

Memory needed

63.2 GB

Fastest

30.1 tok/s

Mistral Medium 3.5 sits at 128B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 38 of the cards we track can hold it.

The least hardware that works is a RTX PRO 5000 72 GB Blackwell. Its 72 GB is enough at Q3_K_M compression, giving roughly 12.0 tokens per second.

At the other end, a H100 NVL 94 GB generates roughly 30.1 tokens per second on it, on the strength of 3,940 GB/s of memory bandwidth.

Background

Mistral Medium 3.5 was published by Mistral AI, in France, in April 2026. industry is the category the publisher falls under.

It works in Language, Multimodal, and is recorded as doing question answering, Language modeling/generation.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

Reading the throughput figures

The median result is around 16.6 tokens per second; 36 cards produce text faster than most people read it.

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

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 Mistral Medium 3.5

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 Mistral Medium 3.5 — around 63.2 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Mistral Medium 3.5 can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Compression is what makes Mistral Medium 3.5 fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for Mistral Medium 3.5. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the H100 NVL 94 GB tops it at 30.1 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs Mistral Medium 3.5 but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Check the card from the other side

Following a card through to its own page shows every other model it can hold, which is the question that follows once Mistral Medium 3.5 is settled.

Answers

Mistral Medium 3.5 — common questions

Why does the quantisation differ between cards for Mistral Medium 3.5?

Each card is shown running the least-compressed copy it can hold, and Mistral Medium 3.5 appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Mistral Medium 3.5 speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 18–48 tok/s on the H100 NVL 94 GB, 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 Medium 3.5?

The smallest card in our catalogue that holds Mistral Medium 3.5 is the RTX PRO 5000 72 GB Blackwell, with 72 GB of memory. It runs the model at Q3_K_M using about 63.2 GB, and produces roughly 12.0 tokens per second. 38 cards in total can run it.

How fast is Mistral Medium 3.5 on a GPU?

It depends on the card. The quickest we calculate is a H100 NVL 94 GB at about 30.1 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 36 of the cards that can run Mistral Medium 3.5 clear that.

How much VRAM does Mistral Medium 3.5 need?

About 63.2 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.

Is Mistral Medium 3.5 open source?

Its weights are published, so Mistral Medium 3.5 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 Medium 3.5 have?

Mistral Medium 3.5 has 128B 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 Mistral Medium 3.5?

Mistral Medium 3.5 was published by Mistral AI, based in France, categorised as industry.

When was Mistral Medium 3.5 released?

Mistral Medium 3.5 was published in April 2026.

What is Mistral Medium 3.5 used for?

Mistral Medium 3.5 works in Language, Multimodal, and is recorded as handling question answering, Language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Mistral Medium 3.5?

The weights for Mistral Medium 3.5 are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run Mistral Medium 3.5 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 20.5 GB. Our figures for Mistral Medium 3.5 assume it is fully resident.

Would two GPUs run Mistral Medium 3.5 faster?

A second card roughly doubles the memory available but not the generation rate. With 38 cards already able to run Mistral Medium 3.5 alone, the case for pairing is weak.

Source

Original publication

Record last updated 27 May 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