Pangu Pro MoE TPS calculator

Open weights Huawei 72B parameters May 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

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 Pangu Pro MoE?

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: Huawei
Organisation type: Industry
Country: China
Published: 28 May 2025
Authors: Yehui Tang, Xiaosong Li, Fangcheng Liu, Wei Guo, Hang Zhou, Yaoyuan Wang, Kai Han, Xianzhi Yu, Jinpeng Li, Hui Zang, Fei Mi, Xiaojun Meng, Zhicheng Liu, Hanting Chen, Binfan Zheng, Can Chen, Youliang Yan, Ruiming Tang, Peifeng Qin, Xinghao Chen, Dacheng Tao, Yunhe Wang (and Other Contributors)

What it does

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

Domain: Language
Task: Language modeling/generation, Question answering, Quantitative reasoning, Mathematical reasoning, Code generation

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: 13,000,000,000,000 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: 1.3 × 10²⁴ FLOP
How it was established: Operation counting

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: Huawei Ascend 800T A2
Chips used: 4,000
Power draw: 2.4 MW

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

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: Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Pangu Pro MoE

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 Pangu Pro MoE

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

A100 PCIe 40 GB

Memory needed

35.9 GB

Fastest

47.1 tok/s

Pangu Pro MoE reaches a parameter count of 72B. That puts it above consumer hardware, into the range where a card is bought for this purpose rather than repurposed for it. The number of cards we track that can hold it: 61.

The least hardware that works is A100 PCIe 40 GB, with a memory capacity of 40 GB, running it at a compression of Q3_K_M and producing around 24.8 tokens per second.

At the other end sits B200, generating roughly 47.1 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Where it came from

Pangu Pro MoE was published by Huawei, in the country recorded as China, during May 2025. The category the publisher falls under is industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Question answering, Quantitative reasoning, Mathematical reasoning, Code generation.

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.

Understanding the speeds

Across every card that can run it, the middle of the range sits at 16.6 tokens per second. Producing text faster than most people read it: 51 of them.

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.

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.

Training and provenance

The training run consumed about 1.3 × 10²⁴ FLOP, on hardware recorded as Huawei Ascend 800T A2. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 13,000,000,000,000 tokens of text.

Step by step

How to choose a GPU for Pangu Pro MoE

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

Start from what it actually needs, which is the requirement of Pangu Pro MoE, needing around 35.9 GB at a compression of Q3_K_M. That figure, not the headline performance of a card, is what decides whether it runs.
02

Set the context length you will work at

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting Pangu Pro MoE.
03

Set a quality floor

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of Q3_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for Pangu Pro MoE. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 47.1 tok/s.
05

Look at the headroom, not just the fit

Tight means it loads and works with no room to raise the context later, in the case of Pangu Pro MoE. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
06

See what else that card runs

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond Pangu Pro MoE.

Answers

Pangu Pro MoE — common questions

Pangu Pro MoE— where can I download it?

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

Pangu Pro MoE— how much compute was used to train it?

Training consumed around 1.3 × 10²⁴ FLOP, on hardware recorded as Huawei Ascend 800T A2. 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.

Pangu Pro MoE— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. The nearest miss we calculate falls short by 15.5 GB. Every figure here assumes the whole model is resident on the card.

Pangu Pro MoE— would two GPUs run it faster?

A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 61. So a second card is rarely the answer here.

Pangu Pro MoE— why does the quantisation differ between cards?

Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Pangu Pro MoE— how accurate are these speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked, which is why each is published as a range rather than a single number. One example: 28–75 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Pangu Pro MoE— what GPU do I need to run it?

The smallest card in our catalogue that holds it is A100 PCIe 40 GB, with a memory capacity of 40 GB. It runs the model at a compression of Q3_K_M using about 35.9 GB, and produces roughly 24.8 tokens per second. The number of cards able to run it in total: 61.

Pangu Pro MoE— how fast is it on a GPU?

It depends on the card. The quickest we calculate is 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 the number of cards clearing that: 51.

Pangu Pro MoE— how much VRAM does it need?

It needs about 35.9 GB at a compression of Q3_K_M, 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.

Pangu Pro MoE— is it open source?

Its weights are published, so it 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.

Pangu Pro MoE— how many parameters does it have?

It has a parameter count of 72B. a total of 71.99B parameters and 16.50 billion active 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.

Pangu Pro MoE— who created it?

It was published by Huawei, based in China, an organisation categorised as industry.

Pangu Pro MoE— when was it released?

It was published in May 2025.

Pangu Pro MoE— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Question answering, Quantitative reasoning, Mathematical reasoning, Code 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.

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