Qwen3-235B-A22B-Thinking (Jul 2025) TPS calculator

Open weights Alibaba 235B parameters July 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 · Q3_K_M · 69.1 tok/s

Fastest card

B200

143 tok/s · 180 GB

Which GPUs can run Qwen3-235B-A22B-Thinking (Jul 2025)?

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.

17 cards match

Calculating
Needs Quantisation Fit
143 tok/s

86–229 · low confidence

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 157.1 GB Q5_K_M Tight
138 tok/s

83–221 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 102.4 GB Q3_K_M Tight
120 tok/s

72–192 · low confidence

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 116.0 GB IQ4_XS Tight
120 tok/s

72–192 · low confidence

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 116.0 GB IQ4_XS Tight
112 tok/s

67–180 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 102.4 GB Q3_K_M Tight
80.1 tok/s

48–128 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 239.1 GB Q8_0 Tight
74.3 tok/s

45–119 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 157.1 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 157.1 GB Q5_K_M Tight
69.1 tok/s

41–111 · low confidence

Radeon Instinct MI250 AMD 128 GB 3,280 GB/s Nov 2021 102.4 GB Q3_K_M Tight
69.1 tok/s

41–111 · low confidence

Radeon Instinct MI250X AMD 128 GB 3,280 GB/s Nov 2021 102.4 GB Q3_K_M Tight
68.1 tok/s

41–109 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 184.4 GB Q6_K Comfortable
64.0 tok/s

38–102 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 239.1 GB Q8_0 Tight
64.0 tok/s

38–102 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 239.1 GB Q8_0 Tight
57.6 tok/s

35–92 · low confidence

Data Center GPU Max 1550 Intel 128 GB 3,280 GB/s Jan 2023 102.4 GB Q3_K_M Tight
56.4 tok/s

34–90 · low confidence

Data Center GPU Max Subsystem Intel 128 GB 3,210 GB/s Jan 2023 102.4 GB Q3_K_M Tight
7.4 tok/s

4–12 · low confidence

GB10 NVIDIA 128 GB 273 GB/s Oct 2025 102.4 GB Q3_K_M Tight
7.4 tok/s

4–12 · low confidence

Jetson T5000 NVIDIA 128 GB 273 GB/s Aug 2025 102.4 GB Q3_K_M 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
25 July 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

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.

Training data
36,000,000,000,000 tokens

36T

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

6 FLOP / parameter / token * 22*10^9 active parameters * 36000000000000 tokens = 4.752e+24 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

Apache 2.0 https://huggingface.co/Qwen/Qwen3-235B-A22B

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

Major Alibaba release

Record confidence
Likely

Sources

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

Reference
Qwen3: Think Deeper, Act Faster
Last updated
12 February 2026

The extremes

What the numbers mean

What it takes to run this model

Minimum card

Radeon Instinct MI250

Memory needed

102.4 GB

Fastest

143 tok/s

At 235B parameters, Qwen3-235B-A22B-Thinking (Jul 2025) 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 smallest card that holds it is the Radeon Instinct MI250 with 128 GB, running it at Q3_K_M and producing around 69.1 tokens per second.

At the other end, a B200 generates roughly 143 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Where it came from

Qwen3-235B-A22B-Thinking (Jul 2025) was published by Alibaba, in China, in July 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 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 69.1 tokens per second, and 15 exceed reading speed outright.

Because it routes each token through a subset of its weights, it produces text at the pace of a much smaller model. The catch is memory: all of it still has to fit, so the speed is a bonus rather than a discount on hardware.

Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.

What went into building it

The training run consumed about 4.8 × 10²⁴ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Around 36,000,000,000,000 tokens went into training it.

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

Step by step

How to choose a GPU for Qwen3-235B-A22B-Thinking (Jul 2025)

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

  1. 01

    Read the memory figure first

    The table lists every card that can hold Qwen3-235B-A22B-Thinking (Jul 2025) — around 102.4 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.

  2. 02

    Match the context to your actual use

    The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Qwen3-235B-A22B-Thinking (Jul 2025) can slip off a card that handles short questions easily.

  3. 03

    Set a quality floor

    The quantisation column varies by card, because a bigger card holds a more accurate copy of Qwen3-235B-A22B-Thinking (Jul 2025) — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.

  4. 04

    Sort by speed

    Ranking by tokens per second for Qwen3-235B-A22B-Thinking (Jul 2025) follows memory bandwidth, not core counts, which is why the B200 tops it at 143 tok/s.

  5. 05

    Look at the headroom, not just the fit

    A tight fit runs Qwen3-235B-A22B-Thinking (Jul 2025) but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.

  6. 06

    Check the card from the other side

    Following a card through to its own page shows every other model it can hold, which is the question that follows once Qwen3-235B-A22B-Thinking (Jul 2025) is settled.

Answers

Qwen3-235B-A22B-Thinking (Jul 2025) — common questions

01

Would two GPUs run Qwen3-235B-A22B-Thinking (Jul 2025) faster?

Capacity adds across cards; throughput does not. Since 17 of the cards we track already hold Qwen3-235B-A22B-Thinking (Jul 2025) on their own, a second card is rarely the answer here.

02

Why does the quantisation differ between cards for Qwen3-235B-A22B-Thinking (Jul 2025)?

Because capacity varies, so does how hard Qwen3-235B-A22B-Thinking (Jul 2025) has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.

03

How accurate are these Qwen3-235B-A22B-Thinking (Jul 2025) speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 86–229 tok/s on the B200 rather than a single number.

04

What GPU do I need to run Qwen3-235B-A22B-Thinking (Jul 2025)?

The smallest card in our catalogue that holds Qwen3-235B-A22B-Thinking (Jul 2025) is the Radeon Instinct MI250, with 128 GB of memory. It runs the model at Q3_K_M using about 102.4 GB, and produces roughly 69.1 tokens per second. 17 cards in total can run it.

05

How fast is Qwen3-235B-A22B-Thinking (Jul 2025) 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-Thinking (Jul 2025) clear that.

06

How much VRAM does Qwen3-235B-A22B-Thinking (Jul 2025) need?

About 102.4 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.

07

Is Qwen3-235B-A22B-Thinking (Jul 2025) open source?

Its weights are published, so Qwen3-235B-A22B-Thinking (Jul 2025) 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.

08

How many parameters does Qwen3-235B-A22B-Thinking (Jul 2025) have?

Qwen3-235B-A22B-Thinking (Jul 2025) 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.

09

Who created Qwen3-235B-A22B-Thinking (Jul 2025)?

Qwen3-235B-A22B-Thinking (Jul 2025) was published by Alibaba, based in China, categorised as industry.

10

When was Qwen3-235B-A22B-Thinking (Jul 2025) released?

Qwen3-235B-A22B-Thinking (Jul 2025) was published in July 2025.

11

What is Qwen3-235B-A22B-Thinking (Jul 2025) used for?

Qwen3-235B-A22B-Thinking (Jul 2025) 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.

12

Where can I download Qwen3-235B-A22B-Thinking (Jul 2025)?

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.

13

How much compute was used to train Qwen3-235B-A22B-Thinking (Jul 2025)?

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.

14

Can I run Qwen3-235B-A22B-Thinking (Jul 2025) if it does not fit in my GPU?

It can be split between the card and system memory, but Qwen3-235B-A22B-Thinking (Jul 2025) generates painfully slowly that way — the nearest miss we calculate is short by 43.3 GB. Nothing on this page assumes offloading.

Source

Original publication

Record last updated 12 February 2026

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.