Qwen3-235B-A22B TPS calculator

Open weights Alibaba 235B 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

17 of 818 cards that can run it

Smallest card that fits

Radeon Instinct MI250

128 GB · IQ4_XS · 62.9 tok/s

Fastest card

B200

143 tok/s · 180 GB

Which GPUs can run Qwen3-235B-A22B?

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

17 cards match

Calculating

					Needs	Quantisation	Fit
143 tok/s 86–229 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	153.0 GB	Q5_K_M	Tight
126 tok/s 75–201 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	112.0 GB	IQ4_XS	Tight
113 tok/s 68–181 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	125.7 GB	Q4_K_M	Tight
113 tok/s 68–181 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	125.7 GB	Q4_K_M	Tight
102 tok/s 61–163 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	112.0 GB	IQ4_XS	Tight
80.1 tok/s 48–128 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	235.1 GB	Q8_0	Tight
74.3 tok/s 45–119 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	153.0 GB	Q5_K_M	Tight
74.3 tok/s 45–119 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	153.0 GB	Q5_K_M	Tight
68.1 tok/s 41–109 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	180.4 GB	Q6_K	Comfortable
64.0 tok/s 38–102 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	235.1 GB	Q8_0	Tight
64.0 tok/s 38–102 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	235.1 GB	Q8_0	Tight
62.9 tok/s 38–101 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	112.0 GB	IQ4_XS	Tight
62.9 tok/s 38–101 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	112.0 GB	IQ4_XS	Tight
52.4 tok/s 31–84 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	112.0 GB	IQ4_XS	Tight
51.3 tok/s 31–82 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	112.0 GB	IQ4_XS	Tight
6.7 tok/s 4–11 · low confidence	GB10 NVIDIA	128 GB	273 GB/s	Oct 2025	112.0 GB	IQ4_XS	Tight
6.7 tok/s 4–11 · low confidence	Jetson T5000 NVIDIA	128 GB	273 GB/s	Aug 2025	112.0 GB	IQ4_XS	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: 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: 235B
Training data: 36,000,000,000,000 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: 4.8 × 10²⁴ 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
Why it is tracked: Discretionary
Record confidence: Likely

Sources

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

Reference: Qwen3: Think Deeper, Act Faster
Last updated: 18 December 2025

The extremes

The ten fastest GPUs for Qwen3-235B-A22B

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 Qwen3-235B-A22B

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

Radeon Instinct MI250

Memory needed

112.0 GB

Fastest

143 tok/s

At 235B parameters, Qwen3-235B-A22B is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 17 of the cards we track can hold it on their own, and all of them are datacentre parts.

The entry point is the Radeon Instinct MI250: 128 GB of memory, IQ4_XS compression, roughly 62.9 tokens per second.

A B200 is the fastest we calculate for it: about 143 tokens per second, from 8,000 GB/s of memory bandwidth.

Background

Qwen3-235B-A22B 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.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the Qwen organisation on Hugging Face.

Reading the throughput figures

Across every card that can run it, the middle of the range is about 68.1 tokens per second, and 15 of them clear the ten tokens per second that roughly matches reading speed.

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.

Training and provenance

Training it took roughly 4.8 × 10²⁴ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 36,000,000,000,000 tokens.

Its inclusion criterion is discretionary.

Step by step

How to choose a GPU for Qwen3-235B-A22B

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

Every card here has been checked against Qwen3-235B-A22B — around 112.0 GB at IQ4_XS. Capacity is the gate — a card either holds it or it does not.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Qwen3-235B-A22B can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold — IQ4_XS on the smallest card that fits. Setting a floor drops the cards that only manage Qwen3-235B-A22B by squeezing it further than you would want.
04

Sort by speed

Ranking by tokens per second for Qwen3-235B-A22B follows memory bandwidth, not core counts, which is why the B200 tops it at 143 tok/s.
05

Look at the headroom, not just the fit

Tight means Qwen3-235B-A22B 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

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Qwen3-235B-A22B.

Answers

Qwen3-235B-A22B — common questions

What is Qwen3-235B-A22B used for?

Qwen3-235B-A22B works in Language, and is recorded as handling language modeling/generation, Question answering, Mathematical reasoning, Quantitative reasoning, Code generation, Translation. 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.

Where can I download Qwen3-235B-A22B?

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 Qwen3-235B-A22B?

Around 4.8 × 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.

Can I run Qwen3-235B-A22B if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded Qwen3-235B-A22B is rarely worth using — the nearest miss we calculate is short by 39.3 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run Qwen3-235B-A22B faster?

A second card roughly doubles the memory available but not the generation rate. With 17 cards already able to run Qwen3-235B-A22B alone, the case for pairing is weak.

Why does the quantisation differ between cards for Qwen3-235B-A22B?

Because capacity varies, so does how hard Qwen3-235B-A22B has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Qwen3-235B-A22B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 86–229 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run Qwen3-235B-A22B?

The smallest card in our catalogue that holds Qwen3-235B-A22B is the Radeon Instinct MI250, with 128 GB of memory. It runs the model at IQ4_XS using about 112.0 GB, and produces roughly 62.9 tokens per second. 17 cards in total can run it.

How fast is Qwen3-235B-A22B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 143 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 15 of the cards that can run Qwen3-235B-A22B clear that.

How much VRAM does Qwen3-235B-A22B need?

About 112.0 GB at IQ4_XS 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 Qwen3-235B-A22B open source?

Its weights are published, so Qwen3-235B-A22B 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 Qwen3-235B-A22B have?

Qwen3-235B-A22B has 235B parameters. 235 billion total parameters and 22 billion activated parameters Number of Layers: 94 Number of Attention Heads (GQA): 64 for Q and 4 for KV Number of Experts: 128 Number of Activated Experts: 8 Context Length: 32,768 natively and 131,072 tokens with YaRN. 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 Qwen3-235B-A22B?

Qwen3-235B-A22B was published by Alibaba, based in China, categorised as industry.

When was Qwen3-235B-A22B released?

Qwen3-235B-A22B was published in April 2025.

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.

All AI models