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 cards that can run it

818 cards we hold specifications for

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 that run 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

Qwen3-235B-A22B reaches a parameter count of 235B. That is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job, and every card able to hold it alone is a datacentre part. The number that can: 17.

The entry point is Radeon Instinct MI250, with a memory capacity of 128 GB, running it at a compression of IQ4_XS and producing around 62.9 tokens per second.

The fastest we calculate for it is B200, generating roughly 143 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

Qwen3-235B-A22B was published by Alibaba, in the country recorded as China, during April 2025. The publishing organisation is categorised as industry.

It works in the domain of Language, and is recorded as performing the task of 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. On Hugging Face it is published under the organisation Qwen.

Reading the throughput figures

Across every card that can run it, the middle of the range sits at 68.1 tokens per second. Producing text faster than most people read it: 15 of them.

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 a computation budget of roughly 4.8 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

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

Its inclusion criterion: 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, needing around 112.0 GB at a compression of 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, because at long context a card that handles short questions easily can be dropped by Qwen3-235B-A22B.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold, reaching a compression of IQ4_XS 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

Sort by speed

Ranking by tokens per second follows memory bandwidth rather than core counts, for Qwen3-235B-A22B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 143 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 Qwen3-235B-A22B. 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 Qwen3-235B-A22B.

Answers

Qwen3-235B-A22B — common questions

Qwen3-235B-A22B— 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, 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.

Qwen3-235B-A22B— where can I download it?

Its weights are published on Hugging Face, under the organisation Qwen. We do not host model files — this site calculates what hardware is needed to run them.

Qwen3-235B-A22B— how much compute was used to train it?

Training consumed 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.

Qwen3-235B-A22B— can I run it 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 model is rarely worth using. The nearest miss we calculate falls short by 39.3 GB. Every figure here assumes the whole model is resident on the card.

Qwen3-235B-A22B— 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: 17. So a second card is rarely the answer here.

Qwen3-235B-A22B— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Qwen3-235B-A22B— how accurate are these speed estimates?

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

Qwen3-235B-A22B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI250, with a memory capacity of 128 GB. It runs the model at a compression of IQ4_XS using about 112.0 GB, and produces roughly 62.9 tokens per second. The number of cards able to run it in total: 17.

Qwen3-235B-A22B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is 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 the number of cards clearing that: 15.

Qwen3-235B-A22B— how much VRAM does it need?

It needs about 112.0 GB at a compression of IQ4_XS, 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.

Qwen3-235B-A22B— 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.

Qwen3-235B-A22B— how many parameters does it have?

It has a parameter count of 235B. 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.

Qwen3-235B-A22B— who created it?

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

Qwen3-235B-A22B— when was it released?

It 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