Mistral Large 2.1 TPS calculator

Open weights Mistral AI 123B parameters November 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

38 cards that can run it

818 cards we hold specifications for

Smallest card that fits

RTX PRO 5000 72 GB Blackwell

72 GB · Q3_K_M · 12.5 tok/s

Fastest card

H100 NVL 94 GB

31.3 tok/s · 94 GB

Which GPUs can run Mistral Large 2.1?

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
31.3 tok/s 19–50 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	75.1 GB	Q4_K_M	Tight
28.4 tok/s 17–45 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	68.0 GB	IQ4_XS	Tight
28.4 tok/s 17–45 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	68.0 GB	IQ4_XS	Tight
27.6 tok/s 17–44 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	132.4 GB	Q8_0	Comfortable
27.6 tok/s 17–44 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	132.4 GB	Q8_0	Comfortable
26.7 tok/s 16–43 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	75.1 GB	Q4_K_M	Tight
26.7 tok/s 16–43 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	75.1 GB	Q4_K_M	Tight
26.7 tok/s 16–43 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	75.1 GB	Q4_K_M	Tight
25.6 tok/s 15–41 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	103.8 GB	Q6_K	Tight
24.5 tok/s 15–39 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	103.8 GB	Q6_K	Comfortable
24.5 tok/s 15–39 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	103.8 GB	Q6_K	Comfortable
22.0 tok/s 13–35 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	132.4 GB	Q8_0	Comfortable
22.0 tok/s 13–35 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	132.4 GB	Q8_0	Comfortable
20.8 tok/s 12–33 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	103.8 GB	Q6_K	Tight
17.3 tok/s 10–28 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	68.0 GB	IQ4_XS	Tight
17.3 tok/s 10–28 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	68.0 GB	IQ4_XS	Tight
17.3 tok/s 10–28 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	68.0 GB	IQ4_XS	Tight
17.3 tok/s 10–28 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	68.0 GB	IQ4_XS	Tight
17.3 tok/s 10–28 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	68.0 GB	IQ4_XS	Tight
17.3 tok/s 10–28 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	68.0 GB	IQ4_XS	Tight
16.4 tok/s 10–26 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	68.0 GB	IQ4_XS	Tight
16.4 tok/s 10–26 · low confidence	A800 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Nov 2022	68.0 GB	IQ4_XS	Tight
16.1 tok/s 10–26 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	132.4 GB	Q8_0	Comfortable
14.3 tok/s 9–23 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	132.4 GB	Q8_0	Comfortable
14.3 tok/s 9–23 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	132.4 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: 15 November 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, Translation, Code generation, Question answering, Retrieval-augmented 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: 123B
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: Unknown

Sources

Where this record came from and when it was last checked.

Reference: Our top-tier large model for high-complexity tasks with the lastest version released November 2024.
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Mistral Large 2.1

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 Large 2.1

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

RTX PRO 5000 72 GB Blackwell

Memory needed

60.8 GB

Fastest

31.3 tok/s

Mistral Large 2.1 reaches a parameter count of 123B. That puts it above consumer hardware, into the range where a card is bought for this purpose rather than repurposed for it. The number of cards we track that can hold it: 38.

At the low end it is handled by RTX PRO 5000 72 GB Blackwell, with a memory capacity of 72 GB, running it at a compression of Q3_K_M and producing around 12.5 tokens per second.

At the other end sits H100 NVL 94 GB, generating roughly 31.3 tokens per second on the strength of a memory bandwidth of 3,940 GB/s.

About this model

Mistral Large 2.1 was published by Mistral AI, in the country recorded as France, during November 2024. It comes out of an organisation categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Translation, Code generation, Question answering, Retrieval-augmented generation.

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

How fast it runs, and why

The median result is around 17.3 tokens per second. Producing text faster than most people read it: 36 of them.

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

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 Mistral Large 2.1

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

Start from what it actually needs, which is the requirement of Mistral Large 2.1, needing around 60.8 GB at a compression of Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Mistral Large 2.1.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of Q3_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

Rank by throughput rather than spec sheet

Ranking by tokens per second follows memory bandwidth rather than core counts, for Mistral Large 2.1. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is H100 NVL 94 GB, at 31.3 tok/s.
05

Read the fit column last

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Mistral Large 2.1. 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

Open the card you have settled on

Following a card through to its own page shows every other model it can hold, which is the question that follows once you have settled on Mistral Large 2.1.

Answers

Mistral Large 2.1 — common questions

Mistral Large 2.1— how much VRAM does it need?

It needs about 60.8 GB at a compression of Q3_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 Large 2.1— 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 Large 2.1— how many parameters does it have?

It has a parameter count of 123B. 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 Large 2.1— who created it?

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

Mistral Large 2.1— when was it released?

It was published in November 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.

Mistral Large 2.1— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Translation, Code generation, Question answering, Retrieval-augmented generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Mistral Large 2.1— 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 Large 2.1— can I run it if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded model is rarely worth using. The nearest miss we calculate falls short by 17.5 GB. Every figure here assumes the whole model is resident on the card.

Mistral Large 2.1— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 38. So a second card is rarely the answer here.

Mistral Large 2.1— 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: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Mistral Large 2.1— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 19–50 tok/s on H100 NVL 94 GB. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Mistral Large 2.1— what GPU do I need to run it?

The smallest card in our catalogue that holds it is RTX PRO 5000 72 GB Blackwell, with a memory capacity of 72 GB. It runs the model at a compression of Q3_K_M using about 60.8 GB, and produces roughly 12.5 tokens per second. The number of cards able to run it in total: 38.

Mistral Large 2.1— how fast is it on a GPU?

It depends on the card. The quickest we calculate is H100 NVL 94 GB, at about 31.3 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: 36.

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