ONE-PEACE TPS calculator

Open weights Alibaba,Huazhong University of Science and Technology 4B parameters May 2023

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 · Q5_K_M · 16.5 tok/s

Fastest card

B200

847 tok/s · 180 GB

Which GPUs can run ONE-PEACE?

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
847 tok/s 508–1,355 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	5.0 GB	Q8_0	Comfortable
847 tok/s 508–1,355 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	5.0 GB	Q8_0	Comfortable
676 tok/s 406–1,082 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	5.0 GB	Q8_0	Comfortable
676 tok/s 406–1,082 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	5.0 GB	Q8_0	Comfortable
541 tok/s 325–866 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	5.0 GB	Q8_0	Comfortable
518 tok/s 311–828 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	5.0 GB	Q8_0	Comfortable
518 tok/s 311–828 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	5.0 GB	Q8_0	Comfortable
496 tok/s 297–793 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	5.0 GB	Q8_0	Comfortable
440 tok/s 264–704 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	5.0 GB	Q8_0	Comfortable
440 tok/s 264–704 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	5.0 GB	Q8_0	Comfortable
440 tok/s 264–704 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	5.0 GB	Q8_0	Comfortable
417 tok/s 250–667 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	5.0 GB	Q8_0	Comfortable
356 tok/s 213–569 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	5.0 GB	Q8_0	Comfortable
356 tok/s 213–569 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	5.0 GB	Q8_0	Comfortable
356 tok/s 213–569 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	5.0 GB	Q8_0	Comfortable
356 tok/s 213–569 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	5.0 GB	Q8_0	Comfortable
356 tok/s 213–569 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	5.0 GB	Q8_0	Comfortable
271 tok/s 163–433 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	5.0 GB	Q8_0	Comfortable
271 tok/s 163–433 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	5.0 GB	Q8_0	Comfortable
226 tok/s 135–361 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	5.0 GB	Q8_0	Comfortable
221 tok/s 133–353 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	5.0 GB	Q8_0	Comfortable
216 tok/s 130–346 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	5.0 GB	Q8_0	Comfortable
216 tok/s 130–346 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	5.0 GB	Q8_0	Comfortable
216 tok/s 130–346 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	5.0 GB	Q8_0	Comfortable
216 tok/s 130–346 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	5.0 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,Huazhong University of Science and Technology
Organisation type: Industry,Academia
Country: China
Published: 18 May 2023
Authors: Peng Wang, Shijie Wang, Junyang Lin, Shuai Bai, Xiaohuan Zhou, Jingren Zhou, Xinggang Wang, Chang Zhou

What it does

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

Domain: Multimodal, Vision, Speech, Language
Task: Image classification, Speech recognition (ASR), Audio question answering, Audio classification, Semantic segmentation
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: 4B
Training data: 490,617,000,000 tokens
Epochs: 4.7

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: 1.8 × 10²⁰ 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 (unrestricted)
Training code: Open source

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: Speculative
Citations: 160

Sources

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

Reference: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run ONE-PEACE

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 ONE-PEACE

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

Tesla C1080

Memory needed

3.6 GB

Fastest

847 tok/s

ONE-PEACE is small enough at 4B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The entry point is the Tesla C1080: 4 GB of memory, Q5_K_M compression, roughly 16.5 tokens per second.

At the other end, a B200 generates roughly 847 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

About this model

ONE-PEACE was published by Alibaba,Huazhong University of Science and Technology, in China, in May 2023. It comes out of industry,Academia.

It works in Multimodal, Vision, Speech, Language, and is recorded as doing image classification, Speech recognition (ASR), Audio question answering, Audio classification, Semantic segmentation.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

How fast it runs, and why

Half the cards that hold it manage more than 28.4 tokens per second, and 776 exceed reading speed outright.

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.

What went into building it

Producing it required around 1.8 × 10²⁰ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Around 490,617,000,000 tokens went into training it.

The reason it appears in this catalogue at all is sOTA improvement.

Step by step

How to choose a GPU for ONE-PEACE

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 ONE-PEACE actually needs — around 3.6 GB at Q5_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

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

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy of ONE-PEACE — Q5_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 ONE-PEACE follows memory bandwidth, not core counts, which is why the B200 tops it at 847 tok/s.
05

Look at the headroom, not just the fit

Tight means ONE-PEACE 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

See what else that card runs

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

Answers

ONE-PEACE — common questions

Why does the quantisation differ between cards for ONE-PEACE?

Each card is shown running the least-compressed copy it can hold, and ONE-PEACE appears at 3 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these ONE-PEACE 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 508–1,355 tok/s on the B200 rather than a single number.

What GPU do I need to run ONE-PEACE?

The smallest card in our catalogue that holds ONE-PEACE is the Tesla C1080, with 4 GB of memory. It runs the model at Q5_K_M using about 3.6 GB, and produces roughly 16.5 tokens per second. 818 cards in total can run it.

How fast is ONE-PEACE on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 847 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 776 of the cards that can run ONE-PEACE clear that.

How much VRAM does ONE-PEACE need?

About 3.6 GB at Q5_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 ONE-PEACE on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 5.0 GB and generating roughly 158 tokens per second — a comfortable fit.

Can I run ONE-PEACE on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 5.0 GB and generating roughly 96.6 tokens per second — a comfortable fit.

Can I run ONE-PEACE on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 5.0 GB and generating roughly 120 tokens per second — a comfortable fit.

Can I run ONE-PEACE on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 5.0 GB and generating roughly 142 tokens per second — a comfortable fit.

Is ONE-PEACE open source?

Its weights are published, so ONE-PEACE 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 ONE-PEACE have?

ONE-PEACE has 4B parameters. "we propose ONE-PEACE, a model with 4B parameters". 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 ONE-PEACE?

ONE-PEACE was published by Alibaba,Huazhong University of Science and Technology, based in China, categorised as industry,Academia.

When was ONE-PEACE released?

ONE-PEACE was published in May 2023. 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 ONE-PEACE used for?

ONE-PEACE works in Multimodal, Vision, Speech, Language, and is recorded as handling image classification, Speech recognition (ASR), Audio question answering, Audio classification, Semantic segmentation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download ONE-PEACE?

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

How much compute was used to train ONE-PEACE?

Around 1.8 × 10²⁰ 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.

Can I run ONE-PEACE 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. Our figures for ONE-PEACE assume it is fully resident.

Would two GPUs run ONE-PEACE faster?

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

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