Voxtral Mini TPS calculator

Open weights Mistral AI 4.7B parameters July 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

818 of 818 cards that can run it

Smallest card that fits

Tesla C1080

4 GB · Q4_K_M · 18.1 tok/s

Fastest card

B200

721 tok/s · 180 GB

Which GPUs can run Voxtral Mini?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
721 tok/s 433–1,153 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	5.7 GB	Q8_0	Comfortable
721 tok/s 433–1,153 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	5.7 GB	Q8_0	Comfortable
576 tok/s 345–921 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	5.7 GB	Q8_0	Comfortable
576 tok/s 345–921 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	5.7 GB	Q8_0	Comfortable
460 tok/s 276–737 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	5.7 GB	Q8_0	Comfortable
441 tok/s 264–705 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	5.7 GB	Q8_0	Comfortable
441 tok/s 264–705 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	5.7 GB	Q8_0	Comfortable
422 tok/s 253–675 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	5.7 GB	Q8_0	Comfortable
374 tok/s 225–599 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	5.7 GB	Q8_0	Comfortable
374 tok/s 225–599 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	5.7 GB	Q8_0	Comfortable
374 tok/s 225–599 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	5.7 GB	Q8_0	Comfortable
355 tok/s 213–568 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	5.7 GB	Q8_0	Comfortable
303 tok/s 182–484 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	5.7 GB	Q8_0	Comfortable
303 tok/s 182–484 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	5.7 GB	Q8_0	Comfortable
303 tok/s 182–484 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	5.7 GB	Q8_0	Comfortable
303 tok/s 182–484 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	5.7 GB	Q8_0	Comfortable
303 tok/s 182–484 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	5.7 GB	Q8_0	Comfortable
231 tok/s 138–369 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	5.7 GB	Q8_0	Comfortable
231 tok/s 138–369 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	5.7 GB	Q8_0	Comfortable
192 tok/s 115–307 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	5.7 GB	Q8_0	Comfortable
188 tok/s 113–301 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	5.7 GB	Q8_0	Comfortable
184 tok/s 110–294 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	5.7 GB	Q8_0	Comfortable
184 tok/s 110–294 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	5.7 GB	Q8_0	Comfortable
184 tok/s 110–294 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	5.7 GB	Q8_0	Comfortable
184 tok/s 110–294 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	5.7 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: 15 July 2025
Authors: Alexander H. Liu, Andy Ehrenberg, Andy Lo, Clément Denoix, Corentin Barreau, Guillaume Lample, Jean-Malo Delignon, Khyathi Raghavi Chandu, Patrick von Platen, Pavankumar Reddy Muddireddy, Sanchit Gandhi, Soham Ghosh, Srijan Mishra, Thomas Foubert, Abhinav Rastogi, Adam Yang, Albert Q. Jiang, Alexandre Sablayrolles, Amélie Héliou, Amélie Martin, Anmol Agarwal, Antoine Roux, Arthur Darcet, Arthur Me…

What it does

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

Domain: Speech, Language
Task: Audio question answering, Speech recognition (ASR), Speech-to-text, Language modeling/generation, Question answering
Base model: Ministral 3B

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: 4.7B
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 frontier open source speech understanding models.
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for Voxtral Mini

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 Voxtral Mini

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

Tesla C1080

Memory needed

3.5 GB

Fastest

721 tok/s

Voxtral Mini is small enough at 4.7B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The entry point is the Tesla C1080: 4 GB of memory, Q4_K_M compression, roughly 18.1 tokens per second.

At the other end, a B200 generates roughly 721 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Background

Voxtral Mini was published by Mistral AI, in France, in July 2025. The organisation is categorised as industry.

It works in Speech, Language, and is recorded as doing audio question answering, Speech recognition (ASR), Speech-to-text, Language modeling/generation, Question answering.

It builds on Ministral 3B, which is why it shares that model's general shape and size.

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.

Reading the throughput figures

Across every card that can run it, the middle of the range is about 28.3 tokens per second, and 771 of them clear the ten tokens per second that roughly matches reading speed.

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.

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 Voxtral Mini

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

Look at what Voxtral Mini actually needs — around 3.5 GB at Q4_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Voxtral Mini stops fitting a card that seemed fine.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q4_K_M on the smallest card that fits. Setting a floor drops the cards that only manage Voxtral Mini by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Sort by speed to see how cards rank for Voxtral Mini. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 721 tok/s.
05

Read the fit column last

Tight means Voxtral Mini 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

See what else that card runs

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Voxtral Mini.

Answers

Voxtral Mini — common questions

How accurate are these Voxtral Mini speed estimates?

These are estimates with real error bars. The fastest result here, 433–1,153 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run Voxtral Mini?

The smallest card in our catalogue that holds Voxtral Mini is the Tesla C1080, with 4 GB of memory. It runs the model at Q4_K_M using about 3.5 GB, and produces roughly 18.1 tokens per second. 818 cards in total can run it.

How fast is Voxtral Mini on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 721 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 771 of the cards that can run Voxtral Mini clear that.

How much VRAM does Voxtral Mini need?

About 3.5 GB at Q4_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.

Can I run Voxtral Mini on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 5.7 GB and generating roughly 134 tokens per second — a comfortable fit.

Can I run Voxtral Mini on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 5.7 GB and generating roughly 82.2 tokens per second — a comfortable fit.

Can I run Voxtral Mini on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 5.7 GB and generating roughly 102 tokens per second — a comfortable fit.

Can I run Voxtral Mini on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 5.7 GB and generating roughly 121 tokens per second — a comfortable fit.

Is Voxtral Mini open source?

Its weights are published, so Voxtral Mini 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 Voxtral Mini have?

Voxtral Mini has 4.7B parameters. Table 1. 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 Voxtral Mini?

Voxtral Mini was published by Mistral AI, based in France, categorised as industry.

When was Voxtral Mini released?

Voxtral Mini was published in July 2025.

What is Voxtral Mini used for?

Voxtral Mini works in Speech, Language, and is recorded as handling audio question answering, Speech recognition (ASR), Speech-to-text, Language modeling/generation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Voxtral Mini?

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 Voxtral Mini 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. Our figures for Voxtral Mini assume it is fully resident.

Would two GPUs run Voxtral Mini faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold Voxtral Mini on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Voxtral Mini?

Because capacity varies, so does how hard Voxtral Mini has to be squeezed — 4 distinct levels appear in the table above. Set a minimum quality to compare at one.

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