Mistral Small 4 TPS calculator

Open weights Mistral AI 119B parameters March 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

43 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI200

64 GB · Q3_K_M · 68.3 tok/s

Fastest card

B200

158 tok/s · 180 GB

Which GPUs can run Mistral Small 4?

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

43 cards match

Calculating

					Needs	Quantisation	Fit
158 tok/s 95–253 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	120.1 GB	Q8_0	Comfortable
158 tok/s 95–253 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	120.1 GB	Q8_0	Comfortable
153 tok/s 92–245 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	64.7 GB	Q4_K_M	Tight
153 tok/s 92–245 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	64.7 GB	Q4_K_M	Tight
147 tok/s 88–235 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	92.4 GB	Q6_K	Comfortable
139 tok/s 83–223 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	78.5 GB	Q5_K_M	Tight
126 tok/s 76–202 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	120.1 GB	Q8_0	Comfortable
126 tok/s 76–202 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	120.1 GB	Q8_0	Comfortable
119 tok/s 72–191 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	92.4 GB	Q6_K	Comfortable
119 tok/s 71–190 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	78.5 GB	Q5_K_M	Tight
119 tok/s 71–190 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	78.5 GB	Q5_K_M	Tight
119 tok/s 71–190 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	78.5 GB	Q5_K_M	Tight
108 tok/s 65–172 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	50.8 GB	Q3_K_M	Tight
96.7 tok/s 58–155 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	120.1 GB	Q8_0	Tight
96.7 tok/s 58–155 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	120.1 GB	Q8_0	Tight
93.1 tok/s 56–149 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	64.7 GB	Q4_K_M	Tight
93.1 tok/s 56–149 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	64.7 GB	Q4_K_M	Tight
93.1 tok/s 56–149 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	64.7 GB	Q4_K_M	Tight
93.1 tok/s 56–149 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	64.7 GB	Q4_K_M	Tight
93.1 tok/s 56–149 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	64.7 GB	Q4_K_M	Tight
93.1 tok/s 56–149 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	64.7 GB	Q4_K_M	Tight
92.5 tok/s 56–148 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	120.1 GB	Q8_0	Comfortable
88.6 tok/s 53–142 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	64.7 GB	Q4_K_M	Tight
88.6 tok/s 53–142 · low confidence	A800 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Nov 2022	64.7 GB	Q4_K_M	Tight
82.1 tok/s 49–131 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	120.1 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: 16 March 2026

What it does

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

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

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: 119B
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)

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 Mistral Small 4
Last updated: 11 August 2026

The extremes

The ten fastest GPUs that run Mistral Small 4

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 Small 4

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 it takes to run this model

Minimum card

Radeon Instinct MI200

Memory needed

50.8 GB

Fastest

158 tok/s

Mistral Small 4 reaches a parameter count of 119B. 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: 43.

The smallest card that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB, running it at a compression of Q3_K_M and producing around 68.3 tokens per second.

The fastest we calculate for it is B200, generating roughly 158 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

Mistral Small 4 was published by Mistral AI, in the country recorded as France, during March 2026. The publishing organisation is categorised as industry.

It works in the domain of Language, Multimodal, Vision, and is recorded as performing the task of language modeling/generation, Question answering.

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

What decides the speed

Across every card that can run it, the middle of the range sits at 92.5 tokens per second. Exceeding reading speed outright: 41 of them.

This is a mixture-of-experts model, which routes each token through only part of itself. It therefore generates far faster than its total size suggests — while still needing every parameter resident in memory, so it is quick without being cheap to hold.

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 Small 4

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 Small 4, needing around 50.8 GB at a compression of Q3_K_M. That figure, not the headline performance of a card, is what decides whether it runs.
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 Mistral Small 4.
03

Decide how much compression you will accept

Compression is what makes a model fit smaller cards, at some cost in accuracy, 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

The speed ordering is effectively an ordering by memory bandwidth, for Mistral Small 4. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 158 tok/s.
05

Look at the headroom, not just the fit

Tight means it loads and works with no room to raise the context later, in the case of Mistral Small 4. 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

See what else that card runs

Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for Mistral Small 4.

Answers

Mistral Small 4 — common questions

Mistral Small 4— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 158 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: 41.

Mistral Small 4— how much VRAM does it need?

It needs about 50.8 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 Small 4— 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 Small 4— how many parameters does it have?

It has a parameter count of 119B. "119B total parameters, with 6B active parameters per token (8B including embedding and output layers).". 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 Small 4— who created it?

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

Mistral Small 4— when was it released?

It was published in March 2026.

Mistral Small 4— what is it used for?

It works in the domain of Language, Multimodal, Vision, and is recorded as handling the task of language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Mistral Small 4— where can I download it?

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

Mistral Small 4— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 21.5 GB. Every figure here assumes the whole model is resident on the card.

Mistral Small 4— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 43. So a second card is rarely the answer here.

Mistral Small 4— 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 Small 4— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 95–253 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Mistral Small 4— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB. It runs the model at a compression of Q3_K_M using about 50.8 GB, and produces roughly 68.3 tokens per second. The number of cards able to run it in total: 43.

Source

Original publication

Record last updated 11 August 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