Qwen3-30B-A3B TPS calculator

Open weights Alibaba 30B parameters April 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

241 of 818 cards that can run it

Smallest card that fits

Xeon Phi 7120P

16 GB · Q3_K_M · 48.4 tok/s

Fastest card

B200

627 tok/s · 180 GB

Which GPUs can run Qwen3-30B-A3B?

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

241 cards match

Calculating

					Needs	Quantisation	Fit
627 tok/s 376–1,004 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	31.2 GB	Q8_0	Comfortable
627 tok/s 376–1,004 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	31.2 GB	Q8_0	Comfortable
501 tok/s 301–802 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	31.2 GB	Q8_0	Comfortable
501 tok/s 301–802 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	31.2 GB	Q8_0	Comfortable
401 tok/s 240–641 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	31.2 GB	Q8_0	Comfortable
384 tok/s 230–614 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	31.2 GB	Q8_0	Comfortable
384 tok/s 230–614 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	31.2 GB	Q8_0	Comfortable
367 tok/s 220–587 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	31.2 GB	Q8_0	Comfortable
326 tok/s 195–521 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	31.2 GB	Q8_0	Comfortable
326 tok/s 195–521 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	31.2 GB	Q8_0	Comfortable
326 tok/s 195–521 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	31.2 GB	Q8_0	Comfortable
309 tok/s 185–494 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	31.2 GB	Q8_0	Comfortable
264 tok/s 158–422 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	31.2 GB	Q8_0	Comfortable
264 tok/s 158–422 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	31.2 GB	Q8_0	Comfortable
264 tok/s 158–422 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	31.2 GB	Q8_0	Comfortable
264 tok/s 158–422 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	31.2 GB	Q8_0	Comfortable
264 tok/s 158–422 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	31.2 GB	Q8_0	Comfortable
239 tok/s 143–383 · low confidence	Tesla V100 SXM2 16 GB NVIDIA	16 GB	1,130 GB/s	Nov 2019	13.7 GB	Q3_K_M	Tight
213 tok/s 128–341 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	24.2 GB	Q6_K	Tight
213 tok/s 128–341 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	24.2 GB	Q6_K	Tight
204 tok/s 122–326 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	24.2 GB	Q6_K	Tight
204 tok/s 122–326 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	24.2 GB	Q6_K	Tight
203 tok/s 122–325 · low confidence	GeForce RTX 5080 NVIDIA	16 GB	960 GB/s	Jan 2025	13.7 GB	Q3_K_M	Tight
201 tok/s 120–321 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	31.2 GB	Q8_0	Comfortable
201 tok/s 120–321 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	31.2 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
Organisation type: Industry
Country: China
Published: 29 April 2025

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, Mathematical reasoning, Quantitative reasoning, Code generation, Translation

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: 30B
Training data: 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: 6.5 × 10²³ 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: Unreleased
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
Record confidence: Likely

Sources

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

Reference: Qwen3: Think Deeper, Act Faster
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for Qwen3-30B-A3B

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 Qwen3-30B-A3B

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

The hardware side

Minimum card

Xeon Phi 7120P

Memory needed

13.7 GB

Fastest

627 tok/s

With 30B parameters, Qwen3-30B-A3B lands in the range a serious desktop card can handle once the weights are compressed. 241 of the cards we track can run it.

At the low end, a Xeon Phi 7120P handles it — 16 GB, at Q3_K_M, for about 48.4 tokens per second.

Top of the range is the B200, at roughly 627 tokens per second thanks to 8,000 GB/s of bandwidth.

Background

Qwen3-30B-A3B was published by Alibaba, in China, in April 2025. The organisation is categorised as industry.

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

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 Qwen organisation on Hugging Face.

Reading the throughput figures

Half the cards that hold it manage more than 95.1 tokens per second, and 239 exceed reading speed outright.

Mixture-of-experts routing is why the speeds here look high for the parameter count. Only a fraction is read per token, but the whole thing has to be loaded.

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

What went into building it

Training it took roughly 6.5 × 10²³ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for Qwen3-30B-A3B

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

The table lists every card that can hold Qwen3-30B-A3B — around 13.7 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Match the context to your actual use

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Qwen3-30B-A3B stops fitting a card that seemed fine.
03

Choose how far you will compress it

Compression is what makes Qwen3-30B-A3B fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for Qwen3-30B-A3B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 627 tok/s.
05

Check the fit verdict before buying

Tight means Qwen3-30B-A3B 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

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 Qwen3-30B-A3B.

Answers

Qwen3-30B-A3B — common questions

How much VRAM does Qwen3-30B-A3B need?

About 13.7 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.

Can I run Qwen3-30B-A3B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q3_K_M, using about 13.7 GB and generating roughly 239 tokens per second — a tight fit.

Can I run Qwen3-30B-A3B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q5_K_M, using about 20.7 GB and generating roughly 188 tokens per second — a tight fit.

Is Qwen3-30B-A3B open source?

Its weights are published, so Qwen3-30B-A3B 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 Qwen3-30B-A3B have?

Qwen3-30B-A3B has 30B parameters. 30 billion total parameters and 3 billion activated parameters Number of Layers: 48 Number of Attention Heads (GQA): 32 for Q and 4 for KV Number of Experts: 128 Number of Activated Experts: 8 Context Length: 32,768. 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 Qwen3-30B-A3B?

Qwen3-30B-A3B was published by Alibaba, based in China, categorised as industry.

When was Qwen3-30B-A3B released?

Qwen3-30B-A3B was published in April 2025.

What is Qwen3-30B-A3B used for?

Qwen3-30B-A3B works in Language, and is recorded as handling language modeling/generation, Question answering, Mathematical reasoning, Quantitative reasoning, Code generation, Translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Qwen3-30B-A3B?

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 Qwen3-30B-A3B?

Around 6.5 × 10²³ 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 Qwen3-30B-A3B 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 6.4 GB. Our figures for Qwen3-30B-A3B assume it is fully resident.

Would two GPUs run Qwen3-30B-A3B faster?

Two cards buy memory rather than speed. That matters for Qwen3-30B-A3B only if one card cannot hold it — 241 can, so a second adds little.

Why does the quantisation differ between cards for Qwen3-30B-A3B?

Each card is shown running the least-compressed copy it can hold, and Qwen3-30B-A3B appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Qwen3-30B-A3B speed estimates?

These are estimates with real error bars. The fastest result here, 376–1,004 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 Qwen3-30B-A3B?

The smallest card in our catalogue that holds Qwen3-30B-A3B is the Xeon Phi 7120P, with 16 GB of memory. It runs the model at Q3_K_M using about 13.7 GB, and produces roughly 48.4 tokens per second. 241 cards in total can run it.

How fast is Qwen3-30B-A3B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 627 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 239 of the cards that can run Qwen3-30B-A3B 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