Qwen2.5-72B TPS calculator

Open weights Alibaba 72.7B parameters September 2024

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 of 818 cards that can run it

Smallest card that fits

A100 PCIe 40 GB

40 GB · Q3_K_M · 24.5 tok/s

Fastest card

B200

46.6 tok/s · 180 GB

Which GPUs can run Qwen2.5-72B?

Set the inputs, read the answer

A longer conversation needs more memory, which can push this model off smaller cards.

Hides cards that would only fit the model by compressing it below this point.

61 cards match

Calculating
Needs Quantisation Fit
46.6 tok/s

40–56

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 76.5 GB Q8_0 Comfortable
46.6 tok/s

40–56

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 76.5 GB Q8_0 Comfortable
37.2 tok/s

22–60 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 76.5 GB Q8_0 Comfortable
37.2 tok/s

22–60 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 76.5 GB Q8_0 Comfortable
29.8 tok/s

18–48 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 76.5 GB Q8_0 Comfortable
28.5 tok/s

24–34

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 76.5 GB Q8_0 Comfortable
28.5 tok/s

24–34

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 76.5 GB Q8_0 Comfortable
28.4 tok/s

24–34

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 59.6 GB Q6_K Comfortable
28.4 tok/s

24–34

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 59.6 GB Q6_K Comfortable
27.3 tok/s

16–44 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 76.5 GB Q8_0 Comfortable
25.2 tok/s

21–30

GRID A100B NVIDIA 48 GB 1,870 GB/s May 2020 42.6 GB Q4_K_M Tight
24.5 tok/s

21–29

A100 PCIe 40 GB NVIDIA 40 GB 1,560 GB/s Jun 2020 34.2 GB Q3_K_M Tight
24.5 tok/s

21–29

A100 SXM4 40 GB NVIDIA 40 GB 1,560 GB/s May 2020 34.2 GB Q3_K_M Tight
24.5 tok/s

21–29

A800 PCIe 40 GB NVIDIA 40 GB 1,560 GB/s Nov 2022 34.2 GB Q3_K_M Tight
24.2 tok/s

15–39 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 76.5 GB Q8_0 Comfortable
24.2 tok/s

15–39 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 76.5 GB Q8_0 Comfortable
24.2 tok/s

15–39 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 76.5 GB Q8_0 Comfortable
23.0 tok/s

20–28

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 76.5 GB Q8_0 Tight
21.0 tok/s

18–25

H100 SXM5 64 GB NVIDIA 64 GB 2,020 GB/s Mar 2023 51.1 GB Q5_K_M Tight
19.6 tok/s

17–23

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 76.5 GB Q8_0 Tight
19.6 tok/s

17–23

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 76.5 GB Q8_0 Tight
19.6 tok/s

17–23

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 76.5 GB Q8_0 Tight
18.0 tok/s

15–22

RTX PRO 5000 Blackwell NVIDIA 48 GB 1,340 GB/s Mar 2025 42.6 GB Q4_K_M Tight
17.3 tok/s

15–21

A100 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Nov 2020 59.6 GB Q6_K Comfortable
17.3 tok/s

15–21

A100X NVIDIA 80 GB 2,040 GB/s Jun 2021 59.6 GB Q6_K 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
19 September 2024
Authors
Qwen Team

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
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
72.7B

72.7B

Training data
18,000,000,000,000 tokens

"In terms of Qwen2.5, the language models, all models are pretrained on our latest large-scale dataset, encompassing up to 18 trillion tokens"

Epochs
1

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
7.8 × 10²⁴ FLOP

Training dataset size was 18 trillion 6ND = 6 * 72.7 billion parameters * 18 trillion tokens = 7.8e24

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.

Data centre
There is no paper to reference, no information about hardware used for training found in media.

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

license: allows commercial. weights only https://huggingface.co/Qwen/Qwen2.5-72B/blob/main/LICENSE

Hugging Face
Qwen

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Likely above 10²³ FLOP
Yes
Why it is tracked
Training cost

High compute, near 1e25

Record confidence
Confident

Sources

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

Reference
Qwen2.5: A Party of Foundation Models!
Last updated
18 December 2025

The extremes

What the numbers mean

Hardware requirements in practice

Minimum card

A100 PCIe 40 GB

Memory needed

34.2 GB

Fastest

46.6 tok/s

Qwen2.5-72B sits at 72.7B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 61 of the cards we track can hold it.

The entry point is the A100 PCIe 40 GB: 40 GB of memory, Q3_K_M compression, roughly 24.5 tokens per second.

Top of the range is the B200, at roughly 46.6 tokens per second thanks to 8,000 GB/s of bandwidth.

About this model

Qwen2.5-72B was published by Alibaba, in China, in September 2024. It comes out of industry.

It works in Language, and is recorded as doing language modeling/generation, Question answering, Quantitative reasoning.

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.

How fast it runs, and why

Across every card that can run it, the middle of the range is about 16.4 tokens per second, and 50 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.

Its attention layout is on file, so the memory figures are computed exactly rather than approximated.

How it was trained

The training run consumed about 7.8 × 10²⁴ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

It was trained on about 18,000,000,000,000 tokens of text.

It is tracked in the underlying dataset for one reason in particular: training cost.

Step by step

How to choose a GPU for Qwen2.5-72B

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

  1. 01

    Start from the memory column

    Look at what Qwen2.5-72B actually needs — around 34.2 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.

  2. 02

    Decide how long your conversations run

    Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Qwen2.5-72B stops fitting a card that seemed fine.

  3. 03

    Choose how far you will compress it

    Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage Qwen2.5-72B by squeezing it further than you would want.

  4. 04

    Sort by speed

    The speed ordering for Qwen2.5-72B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 46.6 tok/s.

  5. 05

    Check the fit verdict before buying

    The fit column separates cards that just manage Qwen2.5-72B from those with room to spare. Buy for the second if the context might grow.

  6. 06

    Open the card you have settled on

    Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Qwen2.5-72B.

Answers

Qwen2.5-72B — common questions

01

Who created Qwen2.5-72B?

Qwen2.5-72B was published by Alibaba, based in China, categorised as industry.

02

When was Qwen2.5-72B released?

Qwen2.5-72B was published in September 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

What is Qwen2.5-72B used for?

Qwen2.5-72B works in Language, and is recorded as handling language modeling/generation, Question answering, Quantitative reasoning. 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.

04

Where can I download Qwen2.5-72B?

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.

05

How much compute was used to train Qwen2.5-72B?

Around 7.8 × 10²⁴ 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.

06

Can I run Qwen2.5-72B 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 13.8 GB. Our figures for Qwen2.5-72B assume it is fully resident.

07

Would two GPUs run Qwen2.5-72B faster?

Capacity adds across cards; throughput does not. Since 61 of the cards we track already hold Qwen2.5-72B on their own, a second card is rarely the answer here.

08

Why does the quantisation differ between cards for Qwen2.5-72B?

A larger card holds a more accurate copy. Across the cards that run Qwen2.5-72B, 5 compression levels are used; the floor control above pins it to one.

09

How accurate are these Qwen2.5-72B speed estimates?

These are estimates with real error bars. The fastest result here, 40–56 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

10

What GPU do I need to run Qwen2.5-72B?

The smallest card in our catalogue that holds Qwen2.5-72B is the A100 PCIe 40 GB, with 40 GB of memory. It runs the model at Q3_K_M using about 34.2 GB, and produces roughly 24.5 tokens per second. 61 cards in total can run it.

11

How fast is Qwen2.5-72B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 46.6 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 50 of the cards that can run Qwen2.5-72B clear that.

12

How much VRAM does Qwen2.5-72B need?

About 34.2 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.

13

Is Qwen2.5-72B open source?

Its weights are published, so Qwen2.5-72B 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.

14

How many parameters does Qwen2.5-72B have?

Qwen2.5-72B has 72.7B parameters. 72.7B. 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.

Source

Original publication

Record last updated 18 December 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.