YOLOv2 TPS calculator

Open weights University of Washington,Allen Institute for AI 51M parameters December 2016

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 · 723 tok/s

Fastest card

B200

66,436 tok/s · 180 GB

Which GPUs can run YOLOv2?

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
66,436 tok/s 39,862–106,298 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.8 GB	Q8_0	Comfortable
66,436 tok/s 39,862–106,298 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.8 GB	Q8_0	Comfortable
53,051 tok/s 31,830–84,881 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.8 GB	Q8_0	Comfortable
53,051 tok/s 31,830–84,881 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.8 GB	Q8_0	Comfortable
42,428 tok/s 25,457–67,884 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.8 GB	Q8_0	Comfortable
40,609 tok/s 24,365–64,974 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.8 GB	Q8_0	Comfortable
40,609 tok/s 24,365–64,974 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.8 GB	Q8_0	Comfortable
38,865 tok/s 23,319–62,184 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.8 GB	Q8_0	Comfortable
34,493 tok/s 20,696–55,188 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.8 GB	Q8_0	Comfortable
34,493 tok/s 20,696–55,188 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.8 GB	Q8_0	Comfortable
34,493 tok/s 20,696–55,188 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.8 GB	Q8_0	Comfortable
32,720 tok/s 19,632–52,352 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
27,903 tok/s 16,742–44,645 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
27,903 tok/s 16,742–44,645 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.8 GB	Q8_0	Comfortable
27,903 tok/s 16,742–44,645 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
27,903 tok/s 16,742–44,645 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
27,903 tok/s 16,742–44,645 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
21,246 tok/s 12,748–33,994 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.8 GB	Q8_0	Comfortable
21,246 tok/s 12,748–33,994 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.8 GB	Q8_0	Comfortable
17,705 tok/s 10,623–28,328 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.8 GB	Q8_0	Comfortable
17,327 tok/s 10,396–27,724 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.8 GB	Q8_0	Comfortable
16,941 tok/s 10,165–27,106 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.8 GB	Q8_0	Comfortable
16,941 tok/s 10,165–27,106 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.8 GB	Q8_0	Comfortable
16,941 tok/s 10,165–27,106 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.8 GB	Q8_0	Comfortable
16,941 tok/s 10,165–27,106 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	0.8 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: University of Washington,Allen Institute for AI
Organisation type: Academia,Research collective
Country: United States of America
Published: 25 December 2016
Authors: Joseph Redmon, Ali Farhadi

What it does

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

Domain: Vision
Task: Object detection
Numerical format: FP32

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: 51M
Training data: 1,280,000 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 (non-commercial)
Training code: Unreleased

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked: Highly cited
Citations: 17,523

Sources

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

Reference: YOLO9000: Better, Faster, Stronger
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run YOLOv2

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 YOLOv2

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

Tesla C1080

Memory needed

0.8 GB

Fastest

66,436 tok/s

YOLOv2 is small enough at 51M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the Tesla C1080 with 4 GB, running it at Q8_0 and producing around 723 tokens per second.

Top of the range is the B200, at roughly 66,436 tokens per second thanks to 8,000 GB/s of bandwidth.

Background

YOLOv2 was published by University of Washington,Allen Institute for AI, in United States of America, in December 2016. academia,Research collective is the category the publisher falls under.

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

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all.

Reading the throughput figures

The median result is around 1,865.5 tokens per second; 818 cards produce text faster than most people read it.

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.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

What went into building it

It was trained on about 1,280,000 tokens of text.

The reason it appears in this catalogue at all is highly cited.

Step by step

How to choose a GPU for YOLOv2

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

Look at what YOLOv2 actually needs — around 0.8 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context YOLOv2 can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage YOLOv2 by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Sort by speed to see how cards rank for YOLOv2. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 66,436 tok/s.
05

Read the fit column last

A tight fit runs YOLOv2 but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Check the card from the other side

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for YOLOv2 alone — a card is usually bought for more than one model.

Answers

YOLOv2 — common questions

Can I run YOLOv2 on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.8 GB and generating roughly 9,384 tokens per second — a comfortable fit.

Can I run YOLOv2 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.8 GB and generating roughly 11,128 tokens per second — a comfortable fit.

Is YOLOv2 open source?

Its weights are published, so YOLOv2 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 YOLOv2 have?

YOLOv2 has 51M parameters. Source: https://resources.wolframcloud.com/NeuralNetRepository/resources/YOLO-V2-Trained-on-MS-COCO-Data_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 YOLOv2?

YOLOv2 was published by University of Washington,Allen Institute for AI, based in United States of America, categorised as academia,Research collective.

When was YOLOv2 released?

YOLOv2 was published in December 2016. 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 YOLOv2 used for?

YOLOv2 works in Vision, and is recorded as handling object detection. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download YOLOv2?

The weights for YOLOv2 are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run YOLOv2 if it does not fit in my GPU?

It can be split between the card and system memory, but YOLOv2 generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run YOLOv2 faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run YOLOv2 alone, the case for pairing is weak.

Why does the quantisation differ between cards for YOLOv2?

A larger card holds a more accurate copy. Across the cards that run YOLOv2, 1 compression levels are used; the floor control above pins it to one.

How accurate are these YOLOv2 speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 39,862–106,298 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run YOLOv2?

The smallest card in our catalogue that holds YOLOv2 is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.8 GB, and produces roughly 723 tokens per second. 818 cards in total can run it.

How fast is YOLOv2 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 66,436 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 YOLOv2 clear that.

How much VRAM does YOLOv2 need?

About 0.8 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 YOLOv2 on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.8 GB and generating roughly 12,374 tokens per second — a comfortable fit.

Can I run YOLOv2 on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.8 GB and generating roughly 7,577 tokens per second — a comfortable fit.

Source

Original publication

Record last updated 25 May 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