Meissonic TPS calculator

Open weights National University of Singapore,Skywork AI,Hong Kong University of Science and Technology (HKUST),University of California (UC) Berkeley,Zhejiang University (ZJU) 1B 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 · 36.9 tok/s

Fastest card

B200

3,388 tok/s · 180 GB

Which GPUs can run Meissonic?

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
3,388 tok/s 2,033–5,421 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.8 GB	Q8_0	Comfortable
3,388 tok/s 2,033–5,421 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.8 GB	Q8_0	Comfortable
2,706 tok/s 1,623–4,329 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.8 GB	Q8_0	Comfortable
2,706 tok/s 1,623–4,329 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.8 GB	Q8_0	Comfortable
2,164 tok/s 1,298–3,462 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.8 GB	Q8_0	Comfortable
2,071 tok/s 1,243–3,314 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.8 GB	Q8_0	Comfortable
2,071 tok/s 1,243–3,314 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.8 GB	Q8_0	Comfortable
1,982 tok/s 1,189–3,171 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.8 GB	Q8_0	Comfortable
1,759 tok/s 1,055–2,815 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.8 GB	Q8_0	Comfortable
1,759 tok/s 1,055–2,815 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.8 GB	Q8_0	Comfortable
1,759 tok/s 1,055–2,815 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.8 GB	Q8_0	Comfortable
1,669 tok/s 1,001–2,670 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,084 tok/s 650–1,734 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.8 GB	Q8_0	Comfortable
1,084 tok/s 650–1,734 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.8 GB	Q8_0	Comfortable
903 tok/s 542–1,445 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.8 GB	Q8_0	Comfortable
884 tok/s 530–1,414 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.8 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: National University of Singapore,Skywork AI,Hong Kong University of Science and Technology (HKUST),University of California (UC) Berkeley,Zhejiang University (ZJU)
Organisation type: Academia,Industry,Academia,Academia,Academia
Country: Singapore, Hong Kong, United States of America, China
Published: 13 March 2025
Authors: Jinbin Bai, Tian Ye, Wei Chow, Enxin Song, Xiangtai Li, Zhen Dong, Lei Zhu, Shuicheng Yan

What it does

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

Domain: Image generation
Task: Text-to-image, Image generation
Base model: CLIP ViT-H/14 - LAION-2B
Numerical format: BF16

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: 1B
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: 1.2 × 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 H100 SXM5 80GB
Chip-hours: 1,152

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
Hugging Face: MeissonFlow

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: Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Meissonic

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 Meissonic

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

1.8 GB

Fastest

3,388 tok/s

Meissonic is small enough at 1B 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 36.9 tokens per second.

The quickest result comes from a B200 at around 3,388 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Where it came from

Meissonic was published by National University of Singapore,Skywork AI,Hong Kong University of Science and Technology (HKUST),University of California (UC) Berkeley,Zhejiang University (ZJU), in Singapore, in March 2025. It comes out of academia,Industry,Academia,Academia,Academia.

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

It is derived from CLIP ViT-H/14 - LAION-2B rather than trained from scratch, which is the usual way a specialised model is produced.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the MeissonFlow organisation on Hugging Face.

Understanding the speeds

The median result is around 95.1 tokens per second; 806 cards produce text faster than most people read it.

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

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

The training run consumed about 1.2 × 10²¹ FLOP, on NVIDIA H100 SXM5 80GB. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Step by step

How to choose a GPU for Meissonic

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

Every card here has been checked against Meissonic — around 1.8 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

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

Choose how far you will compress it

Compression is what makes Meissonic 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

Compare tokens per second, not specifications

The speed ordering for Meissonic is effectively an ordering by memory bandwidth, which is why the B200 tops it at 3,388 tok/s.
05

Check the fit verdict before buying

Tight means Meissonic 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

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

Answers

Meissonic — common questions

How much VRAM does Meissonic need?

About 1.8 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 Meissonic on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.8 GB and generating roughly 631 tokens per second — a comfortable fit.

Can I run Meissonic on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.8 GB and generating roughly 386 tokens per second — a comfortable fit.

Can I run Meissonic on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.8 GB and generating roughly 479 tokens per second — a comfortable fit.

Can I run Meissonic on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.8 GB and generating roughly 568 tokens per second — a comfortable fit.

Is Meissonic open source?

Its weights are published, so Meissonic 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 Meissonic have?

Meissonic has 1B parameters. 1B (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 Meissonic?

Meissonic was published by National University of Singapore,Skywork AI,Hong Kong University of Science and Technology (HKUST),University of California (UC) Berkeley,Zhejiang University (ZJU), based in Singapore, categorised as academia,Industry,Academia,Academia,Academia.

When was Meissonic released?

Meissonic was published in March 2025.

What is Meissonic used for?

Meissonic works in Image generation, and is recorded as handling text-to-image, Image generation. 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 Meissonic?

Its weights are published under the MeissonFlow 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 Meissonic?

Around 1.2 × 10²¹ FLOP, on NVIDIA H100 SXM5 80GB. 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 Meissonic 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 Meissonic is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run Meissonic faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold Meissonic on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Meissonic?

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

How accurate are these Meissonic speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 2,033–5,421 tok/s on the B200 rather than a single number.

What GPU do I need to run Meissonic?

The smallest card in our catalogue that holds Meissonic is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.8 GB, and produces roughly 36.9 tokens per second. 818 cards in total can run it.

How fast is Meissonic on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 3,388 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 806 of the cards that can run Meissonic 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