Mixtral 8x7B TPS calculator

Open weights Mistral AI 46.7B parameters December 2023

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

126 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla M40 24 GB

24 GB · Q3_K_M · 21.7 tok/s

Fastest card

B200

263 tok/s · 180 GB

Which GPUs can run Mixtral 8x7B?

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

126 cards match

Calculating

					Needs	Quantisation	Fit
263 tok/s 158–420 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	48.2 GB	Q8_0	Comfortable
263 tok/s 158–420 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	48.2 GB	Q8_0	Comfortable
210 tok/s 126–336 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	48.2 GB	Q8_0	Comfortable
210 tok/s 126–336 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	48.2 GB	Q8_0	Comfortable
168 tok/s 101–268 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	48.2 GB	Q8_0	Comfortable
161 tok/s 96–257 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	48.2 GB	Q8_0	Comfortable
161 tok/s 96–257 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	48.2 GB	Q8_0	Comfortable
154 tok/s 92–246 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	48.2 GB	Q8_0	Comfortable
142 tok/s 85–227 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	26.4 GB	Q4_K_M	Tight
142 tok/s 85–227 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	26.4 GB	Q4_K_M	Tight
136 tok/s 82–218 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	48.2 GB	Q8_0	Comfortable
136 tok/s 82–218 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	48.2 GB	Q8_0	Comfortable
136 tok/s 82–218 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	48.2 GB	Q8_0	Comfortable
136 tok/s 81–217 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	26.4 GB	Q4_K_M	Tight
136 tok/s 81–217 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	26.4 GB	Q4_K_M	Tight
129 tok/s 78–207 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	48.2 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	21.0 GB	Q3_K_M	Tight
110 tok/s 66–177 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	48.2 GB	Q8_0	Comfortable
110 tok/s 66–177 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	48.2 GB	Q8_0	Comfortable
110 tok/s 66–177 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	48.2 GB	Q8_0	Comfortable
110 tok/s 66–177 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	48.2 GB	Q8_0	Comfortable
110 tok/s 66–177 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	48.2 GB	Q8_0	Comfortable
108 tok/s 65–173 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	21.0 GB	Q3_K_M	Tight
91.5 tok/s 55–146 · low confidence	A100 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Jun 2020	31.8 GB	Q5_K_M	Tight
91.5 tok/s 55–146 · low confidence	A100 SXM4 40 GB NVIDIA	40 GB	1,560 GB/s	May 2020	31.8 GB	Q5_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: 11 December 2023
Authors: Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.

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, Quantitative reasoning, Translation

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: 46.7B
Training data: tokens

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute: 7.7 × 10²³ FLOP
How it was established: Operation counting

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.

Likely above 10²³ FLOP: Yes
Why it is tracked: Significant use
Record confidence: Speculative

Sources

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

Reference: Mixtral of experts: A high quality Sparse Mixture-of-Experts.
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Mixtral 8x7B

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 Mixtral 8x7B

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

Tesla M40 24 GB

Memory needed

21.0 GB

Fastest

263 tok/s

Mixtral 8x7B reaches a parameter count of 46.7B. 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: 126.

At the low end it is handled by Tesla M40 24 GB, with a memory capacity of 24 GB, running it at a compression of Q3_K_M and producing around 21.7 tokens per second.

The fastest we calculate for it is B200, generating roughly 263 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Where it came from

Mixtral 8x7B was published by Mistral AI, in the country recorded as France, during December 2023. 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, Quantitative reasoning, Translation.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. On Hugging Face it is published under the organisation mistralai.

Understanding the speeds

The median result is around 65.8 tokens per second. Exceeding reading speed outright: 122 of them.

Because it routes each token through a subset of its weights, it produces text at the pace of a much smaller model. The catch is memory: all of it still has to fit, so the speed is a bonus rather than a discount on hardware.

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

What went into building it

Training it took a computation budget of roughly 7.7 × 10²³ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The reason it appears in this catalogue at all: significant use.

Step by step

How to choose a GPU for Mixtral 8x7B

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

The table lists every card able to hold Mixtral 8x7B, needing around 21.0 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Match the context to your actual use

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Mixtral 8x7B.
03

Decide how much compression you will accept

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

Sort by speed

Sort by speed to see how cards rank for Mixtral 8x7B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 263 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage it from those with room to spare, in the case of Mixtral 8x7B. 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 Mixtral 8x7B.

Answers

Mixtral 8x7B — common questions

Mixtral 8x7B— 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.

Mixtral 8x7B— how many parameters does it have?

It has a parameter count of 46.7B. 46.7B *sparse* params. 12.9B params used on average: "Concretely, Mixtral has 46.7B total parameters but only uses 12.9B parameters per token. It, therefore, processes input and generates output at the same speed and for the same cost as a 12.9B model.". 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.

Mixtral 8x7B— who created it?

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

Mixtral 8x7B— when was it released?

It was published in December 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Mixtral 8x7B— 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, Quantitative reasoning, Translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Mixtral 8x7B— 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.

Mixtral 8x7B— how much compute was used to train it?

Training consumed around 7.7 × 10²³ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

Mixtral 8x7B— 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 8.4 GB. Every figure here assumes the whole model is resident on the card.

Mixtral 8x7B— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 126. So a second card is rarely the answer here.

Mixtral 8x7B— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 6. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Mixtral 8x7B— 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: 158–420 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Mixtral 8x7B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Tesla M40 24 GB, with a memory capacity of 24 GB. It runs the model at a compression of Q3_K_M using about 21.0 GB, and produces roughly 21.7 tokens per second. The number of cards able to run it in total: 126.

Mixtral 8x7B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 263 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: 122.

Mixtral 8x7B— how much VRAM does it need?

It needs about 21.0 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.

Mixtral 8x7B— 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 Q3_K_M, using about 21.0 GB and generating roughly 119 tokens per second. The fit is tight.

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