Qwen3-Next-80B-A3B TPS calculator

Open weights Alibaba 80B parameters September 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

61 of 818 cards that can run it

Smallest card that fits

A100 PCIe 40 GB

40 GB · Q3_K_M · 124 tok/s

Fastest card

B200

235 tok/s · 180 GB

Which GPUs can run Qwen3-Next-80B-A3B?

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
235 tok/s

141–376 · low confidence

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 80.7 GB Q8_0 Comfortable
235 tok/s

141–376 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 80.7 GB Q8_0 Comfortable
188 tok/s

113–301 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 80.7 GB Q8_0 Comfortable
188 tok/s

113–301 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 80.7 GB Q8_0 Comfortable
150 tok/s

90–240 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 80.7 GB Q8_0 Comfortable
144 tok/s

86–230 · low confidence

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 80.7 GB Q8_0 Comfortable
144 tok/s

86–230 · low confidence

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 80.7 GB Q8_0 Comfortable
144 tok/s

86–230 · low confidence

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 62.0 GB Q6_K Tight
144 tok/s

86–230 · low confidence

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 62.0 GB Q6_K Tight
138 tok/s

83–220 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 80.7 GB Q8_0 Comfortable
135 tok/s

81–216 · low confidence

GRID A100B NVIDIA 48 GB 1,870 GB/s May 2020 38.8 GB IQ4_XS Tight
124 tok/s

74–198 · low confidence

A100 PCIe 40 GB NVIDIA 40 GB 1,560 GB/s Jun 2020 34.1 GB Q3_K_M Tight
124 tok/s

74–198 · low confidence

A100 SXM4 40 GB NVIDIA 40 GB 1,560 GB/s May 2020 34.1 GB Q3_K_M Tight
124 tok/s

74–198 · low confidence

A800 PCIe 40 GB NVIDIA 40 GB 1,560 GB/s Nov 2022 34.1 GB Q3_K_M Tight
122 tok/s

73–195 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 80.7 GB Q8_0 Comfortable
122 tok/s

73–195 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 80.7 GB Q8_0 Comfortable
122 tok/s

73–195 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 80.7 GB Q8_0 Comfortable
116 tok/s

70–185 · low confidence

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 80.7 GB Q8_0 Tight
106 tok/s

64–170 · low confidence

H100 SXM5 64 GB NVIDIA 64 GB 2,020 GB/s Mar 2023 52.7 GB Q5_K_M Tight
98.8 tok/s

59–158 · low confidence

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 80.7 GB Q8_0 Tight
98.8 tok/s

59–158 · low confidence

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 80.7 GB Q8_0 Tight
98.8 tok/s

59–158 · low confidence

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 80.7 GB Q8_0 Tight
96.8 tok/s

58–155 · low confidence

RTX PRO 5000 Blackwell NVIDIA 48 GB 1,340 GB/s Mar 2025 38.8 GB IQ4_XS Tight
87.2 tok/s

52–139 · low confidence

A100 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Nov 2020 62.0 GB Q6_K Tight
87.2 tok/s

52–139 · low confidence

A100X NVIDIA 80 GB 2,040 GB/s Jun 2021 62.0 GB Q6_K 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
10 September 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, System control, Code generation

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
80B

80B - A3B

Training data
15,000,000,000,000 tokens

Training Stage: Pretraining (15T tokens) & Post-training "Qwen3-Next is trained on a uniformly sampled subset (15T tokens) of Qwen3’s 36T-token pretraining corpus"

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
2.7 × 10²³ FLOP

6 FLOP / parameter / token * 3 * 10^9 active parameters * 15 * 10^12 pre-training tokens = 2.7e+23 FLOP "It uses less than 80% of the GPU hours needed by Qwen3-30A-3B, and only 9.3% of the compute cost of Qwen3-32B — while achieving better performance." (Qwen3-30A-3B compute estimation: 6.48e+23 FLOP, Qwen3-32B - 7.0848e+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-Next-80B-A3B-Instruct

Hugging Face
Qwen

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident

Sources

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

Reference
Qwen3-Next: Towards Ultimate Training & Inference Efficiency
Last updated
28 November 2025

The extremes

The ten fastest GPUs for Qwen3-Next-80B-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.

  1. 01 B300 288 GB · 8,000 GB/s · Q8_0 235 tok/s
  2. 02 B200 180 GB · 8,000 GB/s · Q8_0 235 tok/s
  3. 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 188 tok/s
  4. 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 188 tok/s
  5. 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 150 tok/s
  6. 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 144 tok/s
  7. 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 144 tok/s
  8. 08 H800 SXM5 80 GB · 3,360 GB/s · Q6_K 144 tok/s
  9. 09 H100 SXM5 80 GB 80 GB · 3,360 GB/s · Q6_K 144 tok/s
  10. 10 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 138 tok/s

The smallest GPUs that still run Qwen3-Next-80B-A3B

The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.

  1. 01 A800 PCIe 40 GB 40 GB · needs 34.1 GB · Q3_K_M · tight 124 tok/s
  2. 02 A100 PCIe 40 GB 40 GB · needs 34.1 GB · Q3_K_M · tight 124 tok/s
  3. 03 A100 SXM4 40 GB 40 GB · needs 34.1 GB · Q3_K_M · tight 124 tok/s
  4. 04 Radeon PRO W7900D 48 GB · needs 38.8 GB · IQ4_XS · tight 48.7 tok/s
  5. 05 RTX PRO 5000 Blackwell 48 GB · needs 38.8 GB · IQ4_XS · tight 96.8 tok/s
  6. 06 RTX 5880 Ada Generation 48 GB · needs 38.8 GB · IQ4_XS · tight 62.4 tok/s
  7. 07 L20 48 GB · needs 38.8 GB · IQ4_XS · tight 62.4 tok/s
  8. 08 Radeon PRO W7800 48 GB 48 GB · needs 38.8 GB · IQ4_XS · tight 48.7 tok/s
  9. 09 Radeon PRO W7900 48 GB · needs 38.8 GB · IQ4_XS · tight 48.7 tok/s
  10. 10 Data Center GPU Max 1100 48 GB · needs 38.8 GB · IQ4_XS · tight 57.7 tok/s

What the numbers mean

Hardware requirements in practice

Minimum card

A100 PCIe 40 GB

Memory needed

34.1 GB

Fastest

235 tok/s

Qwen3-Next-80B-A3B sits at 80B 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 entry point is the A100 PCIe 40 GB: 40 GB of memory, Q3_K_M compression, roughly 124 tokens per second.

At the other end, a B200 generates roughly 235 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Background

Qwen3-Next-80B-A3B was published by Alibaba, in China, in September 2025. industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Question answering, System control, Code generation.

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. 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 82.9 tokens per second, and 59 of them clear the ten tokens per second that roughly matches reading speed.

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.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

Training and provenance

The training run consumed about 2.7 × 10²³ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Around 15,000,000,000,000 tokens went into training it.

Step by step

How to choose a GPU for Qwen3-Next-80B-A3B

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

  1. 01

    Start from the memory column

    Look at what Qwen3-Next-80B-A3B actually needs — around 34.1 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.

  2. 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-Next-80B-A3B stops fitting a card that seemed fine.

  3. 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 Qwen3-Next-80B-A3B by squeezing it further than you would want.

  4. 04

    Compare tokens per second, not specifications

    Sort by speed to see how cards rank for Qwen3-Next-80B-A3B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 235 tok/s.

  5. 05

    Look at the headroom, not just the fit

    Tight means Qwen3-Next-80B-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.

  6. 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-Next-80B-A3B.

Answers

Qwen3-Next-80B-A3B — common questions

01

When was Qwen3-Next-80B-A3B released?

Qwen3-Next-80B-A3B was published in September 2025.

02

What is Qwen3-Next-80B-A3B used for?

Qwen3-Next-80B-A3B works in Language, and is recorded as handling language modeling/generation, Question answering, System control, Code generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

03

Where can I download Qwen3-Next-80B-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.

04

How much compute was used to train Qwen3-Next-80B-A3B?

Around 2.7 × 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.

05

Can I run Qwen3-Next-80B-A3B if it does not fit in my GPU?

It can be split between the card and system memory, but Qwen3-Next-80B-A3B generates painfully slowly that way — the nearest miss we calculate is short by 14.6 GB. Nothing on this page assumes offloading.

06

Would two GPUs run Qwen3-Next-80B-A3B faster?

A second card roughly doubles the memory available but not the generation rate. With 61 cards already able to run Qwen3-Next-80B-A3B alone, the case for pairing is weak.

07

Why does the quantisation differ between cards for Qwen3-Next-80B-A3B?

Each card is shown running the least-compressed copy it can hold, and Qwen3-Next-80B-A3B appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

08

How accurate are these Qwen3-Next-80B-A3B speed estimates?

These are estimates with real error bars. The fastest result here, 141–376 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

09

What GPU do I need to run Qwen3-Next-80B-A3B?

The smallest card in our catalogue that holds Qwen3-Next-80B-A3B is the A100 PCIe 40 GB, with 40 GB of memory. It runs the model at Q3_K_M using about 34.1 GB, and produces roughly 124 tokens per second. 61 cards in total can run it.

10

How fast is Qwen3-Next-80B-A3B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 235 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 59 of the cards that can run Qwen3-Next-80B-A3B clear that.

11

How much VRAM does Qwen3-Next-80B-A3B need?

About 34.1 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.

12

Is Qwen3-Next-80B-A3B open source?

Its weights are published, so Qwen3-Next-80B-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.

13

How many parameters does Qwen3-Next-80B-A3B have?

Qwen3-Next-80B-A3B has 80B parameters. 80B - A3B. 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.

14

Who created Qwen3-Next-80B-A3B?

Qwen3-Next-80B-A3B was published by Alibaba, based in China, categorised as industry.

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