Zidong Taichu TPS calculator

Open weights Chinese Academy of Sciences,Wuhan AI Computing Center 3.2B parameters August 2021

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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q6_K · 16.7 tok/s

Fastest card

B200

1,059 tok/s · 180 GB

Which GPUs can run Zidong Taichu?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
1,059 tok/s 635–1,694 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	4.1 GB	Q8_0	Comfortable
1,059 tok/s 635–1,694 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	4.1 GB	Q8_0	Comfortable
846 tok/s 507–1,353 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	4.1 GB	Q8_0	Comfortable
846 tok/s 507–1,353 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	4.1 GB	Q8_0	Comfortable
676 tok/s 406–1,082 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	4.1 GB	Q8_0	Comfortable
647 tok/s 388–1,036 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	4.1 GB	Q8_0	Comfortable
647 tok/s 388–1,036 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	4.1 GB	Q8_0	Comfortable
619 tok/s 372–991 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	4.1 GB	Q8_0	Comfortable
550 tok/s 330–880 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	4.1 GB	Q8_0	Comfortable
550 tok/s 330–880 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	4.1 GB	Q8_0	Comfortable
550 tok/s 330–880 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	4.1 GB	Q8_0	Comfortable
521 tok/s 313–834 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	4.1 GB	Q8_0	Comfortable
445 tok/s 267–712 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	4.1 GB	Q8_0	Comfortable
445 tok/s 267–712 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	4.1 GB	Q8_0	Comfortable
445 tok/s 267–712 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	4.1 GB	Q8_0	Comfortable
445 tok/s 267–712 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	4.1 GB	Q8_0	Comfortable
445 tok/s 267–712 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	4.1 GB	Q8_0	Comfortable
339 tok/s 203–542 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	4.1 GB	Q8_0	Comfortable
339 tok/s 203–542 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	4.1 GB	Q8_0	Comfortable
282 tok/s 169–451 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	4.1 GB	Q8_0	Comfortable
276 tok/s 166–442 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	4.1 GB	Q8_0	Comfortable
270 tok/s 162–432 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	4.1 GB	Q8_0	Comfortable
270 tok/s 162–432 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	4.1 GB	Q8_0	Comfortable
270 tok/s 162–432 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	4.1 GB	Q8_0	Comfortable
270 tok/s 162–432 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	4.1 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: Chinese Academy of Sciences,Wuhan AI Computing Center
Organisation type: Academia,Government
Country: China
Published: 11 August 2021

What it does

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

Domain: Multimodal, Speech, Vision, Language
Task: Language modeling/generation, Speech recognition (ASR), Image captioning

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: 3.2B
Training data: tokens

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: 8 × 10²⁰ 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

How it is classified

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

Why it is tracked: Historical significance
Record confidence: Confident

Sources

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

Reference: Zidong Ancestral multi-modal large model
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Zidong Taichu

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 Zidong Taichu

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

Tesla C1080

Memory needed

3.4 GB

Fastest

1,059 tok/s

Zidong Taichu is small enough at 3.2B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The entry point is the Tesla C1080: 4 GB of memory, Q6_K compression, roughly 16.7 tokens per second.

At the other end, a B200 generates roughly 1,059 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

What this model is

Zidong Taichu was published by Chinese Academy of Sciences,Wuhan AI Computing Center, in China, in August 2021. The organisation is categorised as academia,Government.

It works in Multimodal, Speech, Vision, Language, and is recorded as doing language modeling/generation, Speech recognition (ASR), Image captioning.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

What decides the speed

Half the cards that hold it manage more than 33.6 tokens per second, and 779 exceed reading speed outright.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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

Training it took roughly 8 × 10²⁰ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

The reason it appears in this catalogue at all is historical significance.

Step by step

How to choose a GPU for Zidong Taichu

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 Zidong Taichu — around 3.4 GB at Q6_K. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Zidong Taichu stops fitting a card that seemed fine.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q6_K on the smallest card that fits. Setting a floor drops the cards that only manage Zidong Taichu by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for Zidong Taichu follows memory bandwidth, not core counts, which is why the B200 tops it at 1,059 tok/s.
05

Check the fit verdict before buying

A tight fit runs Zidong Taichu but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
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 Zidong Taichu.

Answers

Zidong Taichu — common questions

How many parameters does Zidong Taichu have?

Zidong Taichu has 3.2B parameters. 共32亿参数 translated as A total of 3.2 billion parameters. 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 Zidong Taichu?

Zidong Taichu was published by Chinese Academy of Sciences,Wuhan AI Computing Center, based in China, categorised as academia,Government.

When was Zidong Taichu released?

Zidong Taichu was published in August 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

What is Zidong Taichu used for?

Zidong Taichu works in Multimodal, Speech, Vision, Language, and is recorded as handling language modeling/generation, Speech recognition (ASR), Image captioning. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Zidong Taichu?

The weights for Zidong Taichu are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

How much compute was used to train Zidong Taichu?

Around 8 × 10²⁰ 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 Zidong Taichu if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down. Our figures for Zidong Taichu assume it is fully resident.

Would two GPUs run Zidong Taichu faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold Zidong Taichu on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Zidong Taichu?

Because capacity varies, so does how hard Zidong Taichu has to be squeezed — 2 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Zidong Taichu speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 635–1,694 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 Zidong Taichu?

The smallest card in our catalogue that holds Zidong Taichu is the Tesla C1080, with 4 GB of memory. It runs the model at Q6_K using about 3.4 GB, and produces roughly 16.7 tokens per second. 818 cards in total can run it.

How fast is Zidong Taichu on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,059 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 779 of the cards that can run Zidong Taichu clear that.

How much VRAM does Zidong Taichu need?

About 3.4 GB at Q6_K 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.

Can I run Zidong Taichu on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 4.1 GB and generating roughly 197 tokens per second — a comfortable fit.

Can I run Zidong Taichu on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 4.1 GB and generating roughly 121 tokens per second — a comfortable fit.

Can I run Zidong Taichu on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 4.1 GB and generating roughly 150 tokens per second — a comfortable fit.

Can I run Zidong Taichu on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 4.1 GB and generating roughly 177 tokens per second — a comfortable fit.

Is Zidong Taichu open source?

Its weights are published, so Zidong Taichu 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.

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