Qwen Image TPS calculator

Open weights Alibaba 27B parameters August 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 · Q3_K_M · 9.7 tok/s

Fastest card

B200

125 tok/s · 180 GB

Which GPUs can run Qwen Image?

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
125 tok/s 75–201 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	29.6 GB	Q8_0	Comfortable
125 tok/s 75–201 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	29.6 GB	Q8_0	Comfortable
100 tok/s 60–160 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	29.6 GB	Q8_0	Comfortable
100 tok/s 60–160 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	29.6 GB	Q8_0	Comfortable
80.1 tok/s 48–128 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	29.6 GB	Q8_0	Comfortable
76.7 tok/s 46–123 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	29.6 GB	Q8_0	Comfortable
76.7 tok/s 46–123 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	29.6 GB	Q8_0	Comfortable
73.4 tok/s 44–117 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	29.6 GB	Q8_0	Comfortable
65.2 tok/s 39–104 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	29.6 GB	Q8_0	Comfortable
65.2 tok/s 39–104 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	29.6 GB	Q8_0	Comfortable
65.2 tok/s 39–104 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	29.6 GB	Q8_0	Comfortable
61.8 tok/s 37–99 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	29.6 GB	Q8_0	Comfortable
52.7 tok/s 32–84 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	29.6 GB	Q8_0	Comfortable
52.7 tok/s 32–84 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	29.6 GB	Q8_0	Comfortable
52.7 tok/s 32–84 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	29.6 GB	Q8_0	Comfortable
52.7 tok/s 32–84 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	29.6 GB	Q8_0	Comfortable
52.7 tok/s 32–84 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	29.6 GB	Q8_0	Comfortable
47.8 tok/s 29–77 · low confidence	Tesla V100 SXM2 16 GB NVIDIA	16 GB	1,130 GB/s	Nov 2019	13.9 GB	Q3_K_M	Tight
42.6 tok/s 26–68 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	23.3 GB	Q6_K	Comfortable
42.6 tok/s 26–68 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	23.3 GB	Q6_K	Comfortable
40.8 tok/s 24–65 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	23.3 GB	Q6_K	Comfortable
40.8 tok/s 24–65 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	23.3 GB	Q6_K	Comfortable
40.6 tok/s 24–65 · low confidence	GeForce RTX 5080 NVIDIA	16 GB	960 GB/s	Jan 2025	13.9 GB	Q3_K_M	Tight
40.1 tok/s 24–64 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	29.6 GB	Q8_0	Comfortable
40.1 tok/s 24–64 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	29.6 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: Alibaba
Organisation type: Industry
Country: China
Published: 4 August 2025
Authors: Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kun Yan, Shengming Yin, Shuai Bai, Xiao Xu, Yilei Chen, Yuxiang Chen, Zecheng Tang, Zekai Zhang, Zhengyi Wang

What it does

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

Domain: Image generation, Vision
Task: Image generation, Text-to-image, Image-to-image
Base model: Qwen2.5-VL-7B

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: 27B
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)
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.

Why it is tracked: SOTA improvement
Record confidence: Confident

Sources

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

Reference: Qwen-Image Technical Report
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Qwen Image

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 Qwen Image

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

The hardware side

Minimum card

Xeon Phi 7120P

Memory needed

13.9 GB

Fastest

125 tok/s

With 27B parameters, Qwen Image lands in the range a serious desktop card can handle once the weights are compressed. 241 of the cards we track can run it.

At the low end, a Xeon Phi 7120P handles it — 16 GB, at Q3_K_M, for about 9.7 tokens per second.

Top of the range is the B200, at roughly 125 tokens per second thanks to 8,000 GB/s of bandwidth.

Background

Qwen Image was published by Alibaba, in China, in August 2025. It comes out of industry.

It works in Image generation, Vision, and is recorded as doing image generation, Text-to-image, Image-to-image.

Its starting point was Qwen2.5-VL-7B — most models at this scale are adapted from an existing base rather than built from nothing.

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 Qwen organisation on Hugging Face.

Reading the throughput figures

Across every card that can run it, the middle of the range is about 19.0 tokens per second, and 196 of them clear the ten tokens per second that roughly matches reading speed.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.

How it was trained

Its inclusion criterion is sOTA improvement.

Step by step

How to choose a GPU for Qwen Image

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 Qwen Image actually needs — around 13.9 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Qwen Image.
03

Set a quality floor

Compression is what makes Qwen Image fit smaller cards, at some cost in accuracy — Q3_K_M 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 Qwen Image is effectively an ordering by memory bandwidth, which is why the B200 tops it at 125 tok/s.
05

Read the fit column last

The fit column separates cards that just manage Qwen Image 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 Qwen Image alone — a card is usually bought for more than one model.

Answers

Qwen Image — common questions

How accurate are these Qwen Image speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 75–201 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 Qwen Image?

The smallest card in our catalogue that holds Qwen Image is the Xeon Phi 7120P, with 16 GB of memory. It runs the model at Q3_K_M using about 13.9 GB, and produces roughly 9.7 tokens per second. 241 cards in total can run it.

How fast is Qwen Image on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 125 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 196 of the cards that can run Qwen Image clear that.

How much VRAM does Qwen Image need?

About 13.9 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.

Can I run Qwen Image on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q3_K_M, using about 13.9 GB and generating roughly 47.8 tokens per second — a tight fit.

Can I run Qwen Image on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q5_K_M, using about 20.2 GB and generating roughly 37.5 tokens per second — a tight fit.

Is Qwen Image open source?

Its weights are published, so Qwen Image 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 Qwen Image have?

Qwen Image has 27B parameters. Table 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 Qwen Image?

Qwen Image was published by Alibaba, based in China, categorised as industry.

When was Qwen Image released?

Qwen Image was published in August 2025.

What is Qwen Image used for?

Qwen Image works in Image generation, Vision, and is recorded as handling image generation, Text-to-image, Image-to-image. 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 Qwen Image?

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.

Can I run Qwen Image 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 6.2 GB. Our figures for Qwen Image assume it is fully resident.

Would two GPUs run Qwen Image faster?

Capacity adds across cards; throughput does not. Since 241 of the cards we track already hold Qwen Image on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Qwen Image?

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

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