Qwen2-VL-72B TPS calculator

Open weights Alibaba 72B parameters September 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

61 cards that can run it

818 cards we hold specifications for

Smallest card that fits

A100 PCIe 40 GB

40 GB · Q3_K_M · 24.8 tok/s

Fastest card

B200

47.1 tok/s · 180 GB

Which GPUs can run Qwen2-VL-72B?

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

61 cards match

Calculating

					Needs	Quantisation	Fit
47.1 tok/s 28–75 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	77.8 GB	Q8_0	Comfortable
47.1 tok/s 28–75 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	77.8 GB	Q8_0	Comfortable
37.6 tok/s 23–60 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	77.8 GB	Q8_0	Comfortable
37.6 tok/s 23–60 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	77.8 GB	Q8_0	Comfortable
30.1 tok/s 18–48 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	77.8 GB	Q8_0	Comfortable
28.8 tok/s 17–46 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	77.8 GB	Q8_0	Comfortable
28.8 tok/s 17–46 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	77.8 GB	Q8_0	Comfortable
28.7 tok/s 17–46 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	61.0 GB	Q6_K	Tight
28.7 tok/s 17–46 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	61.0 GB	Q6_K	Tight
27.5 tok/s 17–44 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	77.8 GB	Q8_0	Comfortable
27.0 tok/s 16–43 · low confidence	GRID A100B NVIDIA	48 GB	1,870 GB/s	May 2020	40.1 GB	IQ4_XS	Tight
24.8 tok/s 15–40 · low confidence	A100 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Jun 2020	35.9 GB	Q3_K_M	Tight
24.8 tok/s 15–40 · low confidence	A100 SXM4 40 GB NVIDIA	40 GB	1,560 GB/s	May 2020	35.9 GB	Q3_K_M	Tight
24.8 tok/s 15–40 · low confidence	A800 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Nov 2022	35.9 GB	Q3_K_M	Tight
24.4 tok/s 15–39 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	77.8 GB	Q8_0	Comfortable
24.4 tok/s 15–39 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	77.8 GB	Q8_0	Comfortable
24.4 tok/s 15–39 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	77.8 GB	Q8_0	Comfortable
23.2 tok/s 14–37 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	77.8 GB	Q8_0	Tight
21.2 tok/s 13–34 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	52.6 GB	Q5_K_M	Tight
19.8 tok/s 12–32 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	77.8 GB	Q8_0	Tight
19.8 tok/s 12–32 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	77.8 GB	Q8_0	Tight
19.8 tok/s 12–32 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	77.8 GB	Q8_0	Tight
19.4 tok/s 12–31 · low confidence	RTX PRO 5000 Blackwell NVIDIA	48 GB	1,340 GB/s	Mar 2025	40.1 GB	IQ4_XS	Tight
17.4 tok/s 10–28 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	61.0 GB	Q6_K	Tight
17.4 tok/s 10–28 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	61.0 GB	Q6_K	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: Alibaba
Organisation type: Industry
Country: China
Published: 18 September 2024
Authors: Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, Junyang Lin

What it does

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

Domain: Language, Vision, Multimodal
Task: Visual question answering, Video description, Language modeling/generation, Translation, Question answering, Character recognition (OCR), Quantitative reasoning

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: 72B
Training data: 1,400,000,000,000 tokens

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: 6 × 10²³ FLOP
How it was established: Operation counting

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)
Training code: Unreleased
Hugging Face: Qwen

How it is classified

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

Likely above 10²³ FLOP: Yes
Record confidence: Confident

Sources

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

Reference: Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Qwen2-VL-72B

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 Qwen2-VL-72B

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

A100 PCIe 40 GB

Memory needed

35.9 GB

Fastest

47.1 tok/s

Qwen2-VL-72B sits at 72B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 61 of the cards we track can hold it.

The entry point is the A100 PCIe 40 GB: 40 GB of memory, Q3_K_M compression, roughly 24.8 tokens per second.

A B200 is the fastest we calculate for it: about 47.1 tokens per second, from 8,000 GB/s of memory bandwidth.

Background

Qwen2-VL-72B was published by Alibaba, in China, in September 2024. The organisation is categorised as industry.

It works in Language, Vision, Multimodal, and is recorded as doing visual question answering, Video description, Language modeling/generation, Translation, Question answering, Character recognition (OCR), Quantitative reasoning.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the Qwen organisation on Hugging Face.

Reading the throughput figures

Half the cards that hold it manage more than 16.6 tokens per second, and 51 exceed reading speed outright.

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.

Training and provenance

Producing it required around 6 × 10²³ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Around 1,400,000,000,000 tokens went into training it.

Step by step

How to choose a GPU for Qwen2-VL-72B

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 Qwen2-VL-72B — around 35.9 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Qwen2-VL-72B can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of Qwen2-VL-72B — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Ranking by tokens per second for Qwen2-VL-72B follows memory bandwidth, not core counts, which is why the B200 tops it at 47.1 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage Qwen2-VL-72B from those with room to spare. Buy for the second if the context might grow.
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 Qwen2-VL-72B alone — a card is usually bought for more than one model.

Answers

Qwen2-VL-72B — common questions

Can I run Qwen2-VL-72B if it does not fit in my GPU?

It can be split between the card and system memory, but Qwen2-VL-72B generates painfully slowly that way — the nearest miss we calculate is short by 15.5 GB. Nothing on this page assumes offloading.

Would two GPUs run Qwen2-VL-72B faster?

Two cards buy memory rather than speed. That matters for Qwen2-VL-72B only if one card cannot hold it — 61 can, so a second adds little.

Why does the quantisation differ between cards for Qwen2-VL-72B?

Each card is shown running the least-compressed copy it can hold, and Qwen2-VL-72B appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Qwen2-VL-72B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 28–75 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 Qwen2-VL-72B?

The smallest card in our catalogue that holds Qwen2-VL-72B is the A100 PCIe 40 GB, with 40 GB of memory. It runs the model at Q3_K_M using about 35.9 GB, and produces roughly 24.8 tokens per second. 61 cards in total can run it.

How fast is Qwen2-VL-72B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 47.1 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 51 of the cards that can run Qwen2-VL-72B clear that.

How much VRAM does Qwen2-VL-72B need?

About 35.9 GB at Q3_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.

Is Qwen2-VL-72B open source?

Its weights are published, so Qwen2-VL-72B 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 Qwen2-VL-72B have?

Qwen2-VL-72B has 72B parameters. 72 billion (language model) and 675M (vision encoder). 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 Qwen2-VL-72B?

Qwen2-VL-72B was published by Alibaba, based in China, categorised as industry.

When was Qwen2-VL-72B released?

Qwen2-VL-72B was published in September 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 Qwen2-VL-72B used for?

Qwen2-VL-72B works in Language, Vision, Multimodal, and is recorded as handling visual question answering, Video description, Language modeling/generation, Translation, Question answering, Character recognition (OCR), Quantitative reasoning. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Qwen2-VL-72B?

Its weights are published under the Qwen organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

How much compute was used to train Qwen2-VL-72B?

Around 6 × 10²³ FLOP. 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.

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