Lumina-Image-2.0 TPS calculator

Open weights Shanghai AI Lab,University of Sydney,Chinese University of Hong Kong (CUHK),Shanghai Jiao Tong University,Krea AI 2.6B parameters March 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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 14.2 tok/s

Fastest card

B200

1,303 tok/s · 180 GB

Which GPUs can run Lumina-Image-2.0?

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
1,303 tok/s 782–2,085 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	3.5 GB	Q8_0	Comfortable
1,303 tok/s 782–2,085 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	3.5 GB	Q8_0	Comfortable
1,041 tok/s 624–1,665 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	3.5 GB	Q8_0	Comfortable
1,041 tok/s 624–1,665 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	3.5 GB	Q8_0	Comfortable
832 tok/s 499–1,332 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	3.5 GB	Q8_0	Comfortable
797 tok/s 478–1,275 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.5 GB	Q8_0	Comfortable
797 tok/s 478–1,275 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.5 GB	Q8_0	Comfortable
762 tok/s 457–1,220 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	3.5 GB	Q8_0	Comfortable
677 tok/s 406–1,083 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	3.5 GB	Q8_0	Comfortable
677 tok/s 406–1,083 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	3.5 GB	Q8_0	Comfortable
677 tok/s 406–1,083 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	3.5 GB	Q8_0	Comfortable
642 tok/s 385–1,027 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	3.5 GB	Q8_0	Comfortable
547 tok/s 328–876 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.5 GB	Q8_0	Comfortable
547 tok/s 328–876 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	3.5 GB	Q8_0	Comfortable
547 tok/s 328–876 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	3.5 GB	Q8_0	Comfortable
547 tok/s 328–876 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.5 GB	Q8_0	Comfortable
547 tok/s 328–876 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	3.5 GB	Q8_0	Comfortable
417 tok/s 250–667 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	3.5 GB	Q8_0	Comfortable
417 tok/s 250–667 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	3.5 GB	Q8_0	Comfortable
347 tok/s 208–556 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	3.5 GB	Q8_0	Comfortable
340 tok/s 204–544 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	3.5 GB	Q8_0	Comfortable
332 tok/s 199–532 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	3.5 GB	Q8_0	Comfortable
332 tok/s 199–532 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	3.5 GB	Q8_0	Comfortable
332 tok/s 199–532 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	3.5 GB	Q8_0	Comfortable
332 tok/s 199–532 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	3.5 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: Shanghai AI Lab,University of Sydney,Chinese University of Hong Kong (CUHK),Shanghai Jiao Tong University,Krea AI
Organisation type: Academia,Academia,Academia,Academia,Industry
Country: China, Australia, Hong Kong, United States of America
Published: 27 March 2025
Authors: Qi Qin, Le Zhuo, Yi Xin, Ruoyi Du, Zhen Li, Bin Fu, Yiting Lu, Jiakang Yuan, Xinyue Li, Dongyang Liu, Xiangyang Zhu, Manyuan Zhang, Will Beddow, Erwann Millon, Victor Perez, Wenhai Wang, Conghui He, Bo Zhang, Xiaohong Liu, Hongsheng Li, Yu Qiao, Chang Xu, Peng Gao

What it does

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

Domain: Image generation
Task: Image generation, Text-to-image

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: 2.6B
Training data: 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: 4.8 × 10²¹ FLOP
How it was established: Hardware

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 A100
Chip-hours: 14,184

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: Alpha-VLLM

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: Lumina-Image 2.0: A Unified and Efficient Image Generative Framework
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Lumina-Image-2.0

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 Lumina-Image-2.0

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 you need to run it

Minimum card

Tesla C1080

Memory needed

3.5 GB

Fastest

1,303 tok/s

Lumina-Image-2.0 is small enough at 2.6B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla C1080. Its 4 GB is enough at Q8_0 compression, giving roughly 14.2 tokens per second.

At the other end, a B200 generates roughly 1,303 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Background

Lumina-Image-2.0 was published by Shanghai AI Lab,University of Sydney,Chinese University of Hong Kong (CUHK),Shanghai Jiao Tong University,Krea AI, in China, in March 2025. academia,Academia,Academia,Academia,Industry is the category the publisher falls under.

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

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. It is published under the Alpha-VLLM organisation on Hugging Face.

Reading the throughput figures

The median result is around 36.6 tokens per second; 778 cards produce text faster than most people read it.

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

Producing it required around 4.8 × 10²¹ FLOP of arithmetic, on NVIDIA A100, which is a statement about the training budget rather than about inference.

Step by step

How to choose a GPU for Lumina-Image-2.0

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Read the memory figure first

Look at what Lumina-Image-2.0 actually needs — around 3.5 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Lumina-Image-2.0 can slip off a card that handles short questions easily.
03

Set a quality floor

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 Lumina-Image-2.0 by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for Lumina-Image-2.0 follows memory bandwidth, not core counts, which is why the B200 tops it at 1,303 tok/s.
05

Read the fit column last

A tight fit runs Lumina-Image-2.0 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 Lumina-Image-2.0 alone — a card is usually bought for more than one model.

Answers

Lumina-Image-2.0 — common questions

How accurate are these Lumina-Image-2.0 speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 782–2,085 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 Lumina-Image-2.0?

The smallest card in our catalogue that holds Lumina-Image-2.0 is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 3.5 GB, and produces roughly 14.2 tokens per second. 818 cards in total can run it.

How fast is Lumina-Image-2.0 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,303 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 778 of the cards that can run Lumina-Image-2.0 clear that.

How much VRAM does Lumina-Image-2.0 need?

About 3.5 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 Lumina-Image-2.0 on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 3.5 GB and generating roughly 243 tokens per second — a comfortable fit.

Can I run Lumina-Image-2.0 on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 3.5 GB and generating roughly 149 tokens per second — a comfortable fit.

Can I run Lumina-Image-2.0 on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 3.5 GB and generating roughly 184 tokens per second — a comfortable fit.

Can I run Lumina-Image-2.0 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 3.5 GB and generating roughly 218 tokens per second — a comfortable fit.

Is Lumina-Image-2.0 open source?

Its weights are published, so Lumina-Image-2.0 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 Lumina-Image-2.0 have?

Lumina-Image-2.0 has 2.6B parameters. 2.6B. 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 Lumina-Image-2.0?

Lumina-Image-2.0 was published by Shanghai AI Lab,University of Sydney,Chinese University of Hong Kong (CUHK),Shanghai Jiao Tong University,Krea AI, based in China, categorised as academia,Academia,Academia,Academia,Industry.

When was Lumina-Image-2.0 released?

Lumina-Image-2.0 was published in March 2025.

What is Lumina-Image-2.0 used for?

Lumina-Image-2.0 works in Image generation, and is recorded as handling image generation, Text-to-image. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Lumina-Image-2.0?

Its weights are published under the Alpha-VLLM 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 Lumina-Image-2.0?

Around 4.8 × 10²¹ FLOP, on NVIDIA A100. 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 Lumina-Image-2.0 if it does not fit in my GPU?

It can be split between the card and system memory, but Lumina-Image-2.0 generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run Lumina-Image-2.0 faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run Lumina-Image-2.0 alone, the case for pairing is weak.

Why does the quantisation differ between cards for Lumina-Image-2.0?

Because capacity varies, so does how hard Lumina-Image-2.0 has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

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