Devstral 2 (24B) TPS calculator

Open weights Mistral AI 24B parameters December 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 Devstral 2 (24B)?

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: 9 December 2025

What it does

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

Domain: Language
Task: Language modeling/generation, Coding

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 (restricted use)
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: Likely

Sources

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

Reference: Introducing: Devstral 2 and Mistral Vibe CLI.
Last updated: 8 April 2026

The extremes

The ten fastest GPUs that run Devstral 2 (24B)

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 Devstral 2 (24B)

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

Xeon Phi 7120P

Memory needed

13.8 GB

Fastest

141 tok/s

With 24B parameters, Devstral 2 (24B) 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 entry point is the Xeon Phi 7120P: 16 GB of memory, IQ4_XS compression, roughly 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.

What this model is

Devstral 2 (24B) was published by Mistral AI, in France, in December 2025. It comes out of industry.

It works in Language, and is recorded as doing language modeling/generation, Coding.

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.

What decides the speed

Across every card that can run it, the middle of the range is about 19.4 tokens per second, and 193 of them clear the ten tokens per second that roughly matches reading speed.

It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.

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 Devstral 2 (24B)

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

The table lists every card that can hold Devstral 2 (24B) — around 13.8 GB at IQ4_XS. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Devstral 2 (24B).
03

Decide how much compression you will accept

Compression is what makes Devstral 2 (24B) fit smaller cards, at some cost in accuracy — IQ4_XS on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Compare tokens per second, not specifications

The speed ordering for Devstral 2 (24B) is effectively an ordering by memory bandwidth, which is why the B200 tops it at 141 tok/s.
05

Look at the headroom, not just the fit

Tight means Devstral 2 (24B) 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 Devstral 2 (24B) alone — a card is usually bought for more than one model.

Answers

Devstral 2 (24B) — common questions

What is Devstral 2 (24B) used for?

Devstral 2 (24B) works in Language, and is recorded as handling language modeling/generation, Coding. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Devstral 2 (24B)?

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 Devstral 2 (24B) 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 4.4 GB. Our figures for Devstral 2 (24B) assume it is fully resident.

Would two GPUs run Devstral 2 (24B) faster?

Two cards buy memory rather than speed. That matters for Devstral 2 (24B) only if one card cannot hold it — 241 can, so a second adds little.

Why does the quantisation differ between cards for Devstral 2 (24B)?

A larger card holds a more accurate copy. Across the cards that run Devstral 2 (24B), 4 compression levels are used; the floor control above pins it to one.

How accurate are these Devstral 2 (24B) speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 85–226 tok/s on the B200 rather than a single number.

What GPU do I need to run Devstral 2 (24B)?

The smallest card in our catalogue that holds Devstral 2 (24B) 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 Devstral 2 (24B) 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 Devstral 2 (24B) clear that.

How much VRAM does Devstral 2 (24B) 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 Devstral 2 (24B) 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 Devstral 2 (24B) 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 Devstral 2 (24B) open source?

Its weights are published, so Devstral 2 (24B) 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 Devstral 2 (24B) have?

Devstral 2 (24B) has 24B 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 Devstral 2 (24B)?

Devstral 2 (24B) was published by Mistral AI, based in France, categorised as industry.

When was Devstral 2 (24B) released?

Devstral 2 (24B) was published in December 2025.

Source

Original publication

Record last updated 8 April 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