Step-Audio-Chat 130B TPS calculator

Open weights StepFun 130B parameters February 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

38 cards that can run it

818 cards we hold specifications for

Smallest card that fits

RTX PRO 5000 72 GB Blackwell

72 GB · Q3_K_M · 11.8 tok/s

Fastest card

H100 NVL 94 GB

29.6 tok/s · 94 GB

Which GPUs can run Step-Audio-Chat 130B?

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.

38 cards match

Calculating
Needs Quantisation Fit
29.6 tok/s

18–47 · low confidence

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 79.3 GB Q4_K_M Tight
26.9 tok/s

16–43 · low confidence

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 71.8 GB IQ4_XS Tight
26.9 tok/s

16–43 · low confidence

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 71.8 GB IQ4_XS Tight
26.1 tok/s

16–42 · low confidence

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 139.9 GB Q8_0 Tight
26.1 tok/s

16–42 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 139.9 GB Q8_0 Comfortable
25.3 tok/s

15–40 · low confidence

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 79.3 GB Q4_K_M Tight
25.3 tok/s

15–40 · low confidence

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 79.3 GB Q4_K_M Tight
25.3 tok/s

15–40 · low confidence

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 79.3 GB Q4_K_M Tight
24.2 tok/s

15–39 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 109.6 GB Q6_K Tight
23.2 tok/s

14–37 · low confidence

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 109.6 GB Q6_K Tight
23.2 tok/s

14–37 · low confidence

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 109.6 GB Q6_K Tight
20.8 tok/s

12–33 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 139.9 GB Q8_0 Comfortable
20.8 tok/s

12–33 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 139.9 GB Q8_0 Comfortable
19.7 tok/s

12–31 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 109.6 GB Q6_K Tight
16.3 tok/s

10–26 · low confidence

A100 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Nov 2020 71.8 GB IQ4_XS Tight
16.3 tok/s

10–26 · low confidence

A100X NVIDIA 80 GB 2,040 GB/s Jun 2021 71.8 GB IQ4_XS Tight
16.3 tok/s

10–26 · low confidence

A800 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Aug 2022 71.8 GB IQ4_XS Tight
16.3 tok/s

10–26 · low confidence

H100 CNX NVIDIA 80 GB 2,040 GB/s Mar 2023 71.8 GB IQ4_XS Tight
16.3 tok/s

10–26 · low confidence

H100 PCIe 80 GB NVIDIA 80 GB 2,040 GB/s Oct 2022 71.8 GB IQ4_XS Tight
16.3 tok/s

10–26 · low confidence

H800 PCIe 80 GB NVIDIA 80 GB 2,040 GB/s Mar 2023 71.8 GB IQ4_XS Tight
15.5 tok/s

9–25 · low confidence

A100 PCIe 80 GB NVIDIA 80 GB 1,940 GB/s Jun 2021 71.8 GB IQ4_XS Tight
15.5 tok/s

9–25 · low confidence

A800 PCIe 80 GB NVIDIA 80 GB 1,940 GB/s Nov 2022 71.8 GB IQ4_XS Tight
15.3 tok/s

9–24 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 139.9 GB Q8_0 Comfortable
13.5 tok/s

8–22 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 139.9 GB Q8_0 Comfortable
13.5 tok/s

8–22 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 139.9 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
StepFun
Organisation type
Industry
Country
China
Published
18 February 2025
Authors
Ailin Huang, Boyong Wu, Bruce Wang, Chao Yan, Chen Hu, Chengli Feng, Fei Tian, Feiyu Shen, Jingbei Li, Mingrui Chen, Peng Liu, Ruihang Miao, Wang You, Xi Chen, Xuerui Yang, Yechang Huang, Yuxiang Zhang, Zheng Gong, Zixin Zhang, Hongyu Zhou, Jianjian Sun, Brian Li, Chengting Feng, Changyi Wan, Hanpeng Hu, Jianchang Wu, Jiangjie Zhen, Ranchen Ming, Song Yuan, Xuelin Zhang, Yu Zhou, Bingxin Li, Buyun…

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Speech
Task
Speech synthesis, Speech recognition (ASR), Speech-to-text, Text-to-speech (TTS), Audio question answering, Audio generation, Speech-to-speech
Base model
Step-1

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
130B

130B

Training data
1,668,000,000,000 tokens

Assumingly, 1.1 trillion tokens of audio continuation data (approximately 7,300,000 hours) + 113 billion tokens of TTS (about 700,000 hours) + 105 billion tokens of ASR data (around 650,000 hours) + 350 billion tokens of audio-text alternating data (approximately 2,000,000 hours) = 1668B tokens, 10650000 hours

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
1.9 × 10²⁴ FLOP

base LLM 6.24e+23 FLOP + 6 FLOP / parameter / token * 130*10^9 parameters * 1668000000000 tokens [see training dataset size notes] = 6.24e+23 FLOP + 1.30104e+24 FLOP = 1.92504e+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 for weights https://huggingface.co/stepfun-ai/Step-Audio-Chat Apache 2.0 for inference code https://github.com/stepfun-ai/Step-Audio

Hugging Face
stepfun-ai

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
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
Last updated
28 November 2025

The extremes

The ten fastest GPUs that run Step-Audio-Chat 130B

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 H100 NVL 94 GB 94 GB · 3,940 GB/s · Q4_K_M 29.6 tok/s
  2. 02 H800 SXM5 80 GB · 3,360 GB/s · IQ4_XS 26.9 tok/s
  3. 03 H100 SXM5 80 GB 80 GB · 3,360 GB/s · IQ4_XS 26.9 tok/s
  4. 04 B300 288 GB · 8,000 GB/s · Q8_0 26.1 tok/s
  5. 05 B200 180 GB · 8,000 GB/s · Q8_0 26.1 tok/s
  6. 06 H100 PCIe 96 GB 96 GB · 3,360 GB/s · Q4_K_M 25.3 tok/s
  7. 07 H100 SXM5 94 GB 94 GB · 3,360 GB/s · Q4_K_M 25.3 tok/s
  8. 08 H100 SXM5 96 GB 96 GB · 3,360 GB/s · Q4_K_M 25.3 tok/s
  9. 09 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q6_K 24.2 tok/s
  10. 10 H200 NVL 141 GB · 4,890 GB/s · Q6_K 23.2 tok/s

The smallest GPUs that still run Step-Audio-Chat 130B

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

  1. 01 RTX PRO 5000 72 GB Blackwell 72 GB · needs 64.2 GB · Q3_K_M · tight 11.8 tok/s
  2. 02 H100 CNX 80 GB · needs 71.8 GB · IQ4_XS · tight 16.3 tok/s
  3. 03 H800 PCIe 80 GB 80 GB · needs 71.8 GB · IQ4_XS · tight 16.3 tok/s
  4. 04 H800 SXM5 80 GB · needs 71.8 GB · IQ4_XS · tight 26.9 tok/s
  5. 05 A800 PCIe 80 GB 80 GB · needs 71.8 GB · IQ4_XS · tight 15.5 tok/s
  6. 06 H100 PCIe 80 GB 80 GB · needs 71.8 GB · IQ4_XS · tight 16.3 tok/s
  7. 07 H100 SXM5 80 GB 80 GB · needs 71.8 GB · IQ4_XS · tight 26.9 tok/s
  8. 08 A800 SXM4 80 GB 80 GB · needs 71.8 GB · IQ4_XS · tight 16.3 tok/s
  9. 09 A100 PCIe 80 GB 80 GB · needs 71.8 GB · IQ4_XS · tight 15.5 tok/s
  10. 10 A100X 80 GB · needs 71.8 GB · IQ4_XS · tight 16.3 tok/s

What the numbers mean

What you need to run it

Minimum card

RTX PRO 5000 72 GB Blackwell

Memory needed

64.2 GB

Fastest

29.6 tok/s

Step-Audio-Chat 130B sits at 130B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 38 of the cards we track can hold it.

The least hardware that works is a RTX PRO 5000 72 GB Blackwell. Its 72 GB is enough at Q3_K_M compression, giving roughly 11.8 tokens per second.

The quickest result comes from a H100 NVL 94 GB at around 29.6 tokens per second — its 3,940 GB/s of bandwidth is what buys that.

Where it came from

Step-Audio-Chat 130B was published by StepFun, in China, in February 2025. It comes out of industry.

It works in Speech, and is recorded as doing speech synthesis, Speech recognition (ASR), Speech-to-text, Text-to-speech (TTS), Audio question answering, Audio generation, Speech-to-speech.

It is derived from Step-1 rather than trained from scratch, which is the usual way a specialised model is produced.

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 stepfun-ai organisation on Hugging Face.

Understanding the speeds

Half the cards that hold it manage more than 16.3 tokens per second, and 35 exceed reading speed outright.

It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.

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

Producing it required around 1.9 × 10²⁴ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Around 1,668,000,000,000 tokens went into training it.

Step by step

How to choose a GPU for Step-Audio-Chat 130B

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

    Every card here has been checked against Step-Audio-Chat 130B — around 64.2 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.

  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 Step-Audio-Chat 130B stops fitting a card that seemed fine.

  3. 03

    Choose how far you will compress it

    The quantisation column varies by card, because a bigger card holds a more accurate copy of Step-Audio-Chat 130B — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.

  4. 04

    Rank by throughput rather than spec sheet

    Sort by speed to see how cards rank for Step-Audio-Chat 130B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the H100 NVL 94 GB tops it at 29.6 tok/s.

  5. 05

    Read the fit column last

    A tight fit runs Step-Audio-Chat 130B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.

  6. 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 Step-Audio-Chat 130B.

Answers

Step-Audio-Chat 130B — common questions

01

Why does the quantisation differ between cards for Step-Audio-Chat 130B?

A larger card holds a more accurate copy. Across the cards that run Step-Audio-Chat 130B, 5 compression levels are used; the floor control above pins it to one.

02

How accurate are these Step-Audio-Chat 130B 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 18–47 tok/s on the H100 NVL 94 GB rather than a single number.

03

What GPU do I need to run Step-Audio-Chat 130B?

The smallest card in our catalogue that holds Step-Audio-Chat 130B is the RTX PRO 5000 72 GB Blackwell, with 72 GB of memory. It runs the model at Q3_K_M using about 64.2 GB, and produces roughly 11.8 tokens per second. 38 cards in total can run it.

04

How fast is Step-Audio-Chat 130B on a GPU?

It depends on the card. The quickest we calculate is a H100 NVL 94 GB at about 29.6 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 35 of the cards that can run Step-Audio-Chat 130B clear that.

05

How much VRAM does Step-Audio-Chat 130B need?

About 64.2 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.

06

Is Step-Audio-Chat 130B open source?

Its weights are published, so Step-Audio-Chat 130B 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.

07

How many parameters does Step-Audio-Chat 130B have?

Step-Audio-Chat 130B has 130B parameters. 130B. 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.

08

Who created Step-Audio-Chat 130B?

Step-Audio-Chat 130B was published by StepFun, based in China, categorised as industry.

09

When was Step-Audio-Chat 130B released?

Step-Audio-Chat 130B was published in February 2025.

10

What is Step-Audio-Chat 130B used for?

Step-Audio-Chat 130B works in Speech, and is recorded as handling speech synthesis, Speech recognition (ASR), Speech-to-text, Text-to-speech (TTS), Audio question answering, Audio generation, Speech-to-speech. 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.

11

Where can I download Step-Audio-Chat 130B?

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

12

How much compute was used to train Step-Audio-Chat 130B?

Around 1.9 × 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.

13

Can I run Step-Audio-Chat 130B if it does not fit in my GPU?

It can be split between the card and system memory, but Step-Audio-Chat 130B generates painfully slowly that way — the nearest miss we calculate is short by 21.7 GB. Nothing on this page assumes offloading.

14

Would two GPUs run Step-Audio-Chat 130B faster?

A second card roughly doubles the memory available but not the generation rate. With 38 cards already able to run Step-Audio-Chat 130B alone, the case for pairing is weak.

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