Qwen2.5 Instruct (72B) TPS calculator
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 we hold specifications for
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 Instruct (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
- Code generation, Code autocompletion, Quantitative reasoning, Question answering, Language modeling/generation
- Base model
- Qwen2.5-72B
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
- Training data
- tokens
Number of Parameters: 72.7B Number of Paramaters (Non-Embedding): 70.0B
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
- 7.9 × 10²⁴ FLOP
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 (restricted use)
- Training code
- Unreleased
- Hugging Face
- Qwen
requires permission to use in applications with 100M+ users https://huggingface.co/Qwen/Qwen2.5-72B-Instruct seems that there is no pretraining code here https://github.com/QwenLM/Qwen3
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
- 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
- 11 February 2026
The extremes
The ten fastest GPUs that run Qwen2.5 Instruct (72B)
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.
- 01 B300 288 GB · 8,000 GB/s · Q8_0 46.6 tok/s
- 02 B200 180 GB · 8,000 GB/s · Q8_0 46.6 tok/s
- 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 37.2 tok/s
- 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 37.2 tok/s
- 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 29.8 tok/s
- 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 28.5 tok/s
- 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 28.5 tok/s
- 08 H800 SXM5 80 GB · 3,360 GB/s · Q6_K 28.4 tok/s
- 09 H100 SXM5 80 GB 80 GB · 3,360 GB/s · Q6_K 28.4 tok/s
- 10 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 27.3 tok/s
The smallest GPUs that still run Qwen2.5 Instruct (72B)
The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.
- 01 A800 PCIe 40 GB 40 GB · needs 34.2 GB · Q3_K_M · tight 24.5 tok/s
- 02 A100 PCIe 40 GB 40 GB · needs 34.2 GB · Q3_K_M · tight 24.5 tok/s
- 03 A100 SXM4 40 GB 40 GB · needs 34.2 GB · Q3_K_M · tight 24.5 tok/s
- 04 Radeon PRO W7900D 48 GB · needs 42.6 GB · Q4_K_M · tight 9.1 tok/s
- 05 RTX PRO 5000 Blackwell 48 GB · needs 42.6 GB · Q4_K_M · tight 18.0 tok/s
- 06 RTX 5880 Ada Generation 48 GB · needs 42.6 GB · Q4_K_M · tight 11.6 tok/s
- 07 L20 48 GB · needs 42.6 GB · Q4_K_M · tight 11.6 tok/s
- 08 Radeon PRO W7800 48 GB 48 GB · needs 42.6 GB · Q4_K_M · tight 9.1 tok/s
- 09 Radeon PRO W7900 48 GB · needs 42.6 GB · Q4_K_M · tight 9.1 tok/s
- 10 Data Center GPU Max 1100 48 GB · needs 42.6 GB · Q4_K_M · tight 10.8 tok/s
What the numbers mean
What you need to run it
Minimum card
A100 PCIe 40 GB
Memory needed
34.2 GB
Fastest
46.6 tok/s
Qwen2.5 Instruct (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 least hardware that works is a A100 PCIe 40 GB. Its 40 GB is enough at Q3_K_M compression, giving 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.
Where it came from
Qwen2.5 Instruct (72B) was published by Alibaba, in China, in September 2024. The organisation is categorised as industry.
It works in Language, and is recorded as doing code generation, Code autocompletion, Quantitative reasoning, Question answering, Language modeling/generation.
It is derived from Qwen2.5-72B rather than trained from scratch, which is the usual way a specialised model is produced.
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.
Understanding the speeds
Half the cards that hold it manage more than 16.4 tokens per second, and 50 exceed reading speed outright.
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.
Because the architecture is recorded, the memory column is derived rather than estimated.
Training and provenance
The training run consumed about 7.9 × 10²⁴ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Its inclusion criterion is training cost.
Step by step
How to choose a GPU for Qwen2.5 Instruct (72B)
The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.
-
01
Check what it needs before anything else
Look at what Qwen2.5 Instruct (72B) actually needs — around 34.2 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
-
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 Qwen2.5 Instruct (72B) stops fitting a card that seemed fine.
-
03
Decide how much compression you will accept
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 Instruct (72B) by squeezing it further than you would want.
-
04
Compare tokens per second, not specifications
Sort by speed to see how cards rank for Qwen2.5 Instruct (72B). It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 46.6 tok/s.
-
05
Look at the headroom, not just the fit
A tight fit runs Qwen2.5 Instruct (72B) but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
-
06
See what else that card runs
Following a card through to its own page shows every other model it can hold, which is the question that follows once Qwen2.5 Instruct (72B) is settled.
Answers
Qwen2.5 Instruct (72B) — common questions
Where can I download Qwen2.5 Instruct (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.
How much compute was used to train Qwen2.5 Instruct (72B)?
Around 7.9 × 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.
Can I run Qwen2.5 Instruct (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 Instruct (72B) assume it is fully resident.
Would two GPUs run Qwen2.5 Instruct (72B) faster?
Capacity adds across cards; throughput does not. Since 61 of the cards we track already hold Qwen2.5 Instruct (72B) on their own, a second card is rarely the answer here.
Why does the quantisation differ between cards for Qwen2.5 Instruct (72B)?
Each card is shown running the least-compressed copy it can hold, and Qwen2.5 Instruct (72B) appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.
How accurate are these Qwen2.5 Instruct (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.
What GPU do I need to run Qwen2.5 Instruct (72B)?
The smallest card in our catalogue that holds Qwen2.5 Instruct (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.
How fast is Qwen2.5 Instruct (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 Instruct (72B) clear that.
How much VRAM does Qwen2.5 Instruct (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.
Is Qwen2.5 Instruct (72B) open source?
Its weights are published, so Qwen2.5 Instruct (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.
How many parameters does Qwen2.5 Instruct (72B) have?
Qwen2.5 Instruct (72B) has 72.7B parameters. Number of Parameters: 72.7B Number of Paramaters (Non-Embedding): 70.0B. 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 Qwen2.5 Instruct (72B)?
Qwen2.5 Instruct (72B) was published by Alibaba, based in China, categorised as industry.
When was Qwen2.5 Instruct (72B) released?
Qwen2.5 Instruct (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.
What is Qwen2.5 Instruct (72B) used for?
Qwen2.5 Instruct (72B) works in Language, and is recorded as handling code generation, Code autocompletion, Quantitative reasoning, Question answering, Language modeling/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.
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.