YOLOv10-X TPS calculator

Open weights Tsinghua University 29.5M parameters May 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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 1,250 tok/s

Fastest card

B200

114,855 tok/s · 180 GB

Which GPUs can run YOLOv10-X?

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
114,855 tok/s 68,913–183,769 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.7 GB	Q8_0	Comfortable
114,855 tok/s 68,913–183,769 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.7 GB	Q8_0	Comfortable
91,715 tok/s 55,029–146,744 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.7 GB	Q8_0	Comfortable
91,715 tok/s 55,029–146,744 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.7 GB	Q8_0	Comfortable
73,350 tok/s 44,010–117,359 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
70,205 tok/s 42,123–112,329 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.7 GB	Q8_0	Comfortable
70,205 tok/s 42,123–112,329 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.7 GB	Q8_0	Comfortable
67,190 tok/s 40,314–107,505 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.7 GB	Q8_0	Comfortable
59,632 tok/s 35,779–95,410 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
59,632 tok/s 35,779–95,410 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
59,632 tok/s 35,779–95,410 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
56,566 tok/s 33,940–90,506 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
48,239 tok/s 28,944–77,183 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
48,239 tok/s 28,944–77,183 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.7 GB	Q8_0	Comfortable
48,239 tok/s 28,944–77,183 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
48,239 tok/s 28,944–77,183 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
48,239 tok/s 28,944–77,183 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
36,731 tok/s 22,038–58,769 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.7 GB	Q8_0	Comfortable
36,731 tok/s 22,038–58,769 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.7 GB	Q8_0	Comfortable
30,609 tok/s 18,365–48,974 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
29,956 tok/s 17,973–47,929 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
29,288 tok/s 17,573–46,861 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.7 GB	Q8_0	Comfortable
29,288 tok/s 17,573–46,861 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.7 GB	Q8_0	Comfortable
29,288 tok/s 17,573–46,861 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.7 GB	Q8_0	Comfortable
29,288 tok/s 17,573–46,861 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	0.7 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: Tsinghua University
Organisation type: Academia
Country: China
Published: 23 May 2024
Authors: Ao Wang, Hui Chen, Lihao Liu, Kai Chen, Zijia Lin, Jungong Han, Guiguang Ding

What it does

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

Domain: Vision
Task: Object detection

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: 29.5M
Training data: tokens
Epochs: 500

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: 1.5 × 10¹⁷ FLOP
How it was established: Operation counting

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware: NVIDIA GeForce RTX 3090 Ti
Chips used: 8
Power draw: 7.1 kW

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: Open source

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: YOLOv10: Real-Time End-to-End Object Detection
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run YOLOv10-X

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 YOLOv10-X

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

0.7 GB

Fastest

114,855 tok/s

YOLOv10-X is small enough at 29.5M 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, Q8_0 compression, roughly 1,250 tokens per second.

At the other end, a B200 generates roughly 114,855 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

What this model is

YOLOv10-X was published by Tsinghua University, in China, in May 2024. The organisation is categorised as academia.

It works in Vision, and is recorded as doing object detection.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

What decides the speed

Half the cards that hold it manage more than 3,225.1 tokens per second, and 818 exceed reading speed outright.

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.

What went into building it

Training it took roughly 1.5 × 10¹⁷ FLOP of computation, on NVIDIA GeForce RTX 3090 Ti — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for YOLOv10-X

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

The table lists every card that can hold YOLOv10-X — around 0.7 GB at Q8_0. That figure, not the card's headline performance, is what decides whether it runs.
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 YOLOv10-X stops fitting a card that seemed fine.
03

Set a quality floor

Compression is what makes YOLOv10-X fit smaller cards, at some cost in accuracy — Q8_0 on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Sort by speed

Ranking by tokens per second for YOLOv10-X follows memory bandwidth, not core counts, which is why the B200 tops it at 114,855 tok/s.
05

Look at the headroom, not just the fit

Tight means YOLOv10-X 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

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond YOLOv10-X.

Answers

YOLOv10-X — common questions

How much VRAM does YOLOv10-X need?

About 0.7 GB at Q8_0 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 YOLOv10-X on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.7 GB and generating roughly 21,392 tokens per second — a comfortable fit.

Can I run YOLOv10-X on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.7 GB and generating roughly 13,099 tokens per second — a comfortable fit.

Can I run YOLOv10-X on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.7 GB and generating roughly 16,223 tokens per second — a comfortable fit.

Can I run YOLOv10-X on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.7 GB and generating roughly 19,238 tokens per second — a comfortable fit.

Is YOLOv10-X open source?

Its weights are published, so YOLOv10-X 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 YOLOv10-X have?

YOLOv10-X has 29.5M parameters. 29.5M. 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 YOLOv10-X?

YOLOv10-X was published by Tsinghua University, based in China, categorised as academia.

When was YOLOv10-X released?

YOLOv10-X was published in May 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.

What is YOLOv10-X used for?

YOLOv10-X works in Vision, and is recorded as handling object detection. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Where can I download YOLOv10-X?

The weights for YOLOv10-X are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

How much compute was used to train YOLOv10-X?

Around 1.5 × 10¹⁷ FLOP, on NVIDIA GeForce RTX 3090 Ti. 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.

Can I run YOLOv10-X 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 YOLOv10-X is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run YOLOv10-X faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run YOLOv10-X alone, the case for pairing is weak.

Why does the quantisation differ between cards for YOLOv10-X?

Each card is shown running the least-compressed copy it can hold, and YOLOv10-X appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these YOLOv10-X speed estimates?

These are estimates with real error bars. The fastest result here, 68,913–183,769 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 YOLOv10-X?

The smallest card in our catalogue that holds YOLOv10-X is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.7 GB, and produces roughly 1,250 tokens per second. 818 cards in total can run it.

How fast is YOLOv10-X on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 114,855 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 818 of the cards that can run YOLOv10-X clear that.

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