Jiutian TPS calculator

Open weights China Mobile 13.9B parameters October 2023

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

306 cards that can run it

818 cards we hold specifications for

Smallest card that fits

P102-101

10 GB · IQ4_XS · 20.4 tok/s

Fastest card

B200

244 tok/s · 180 GB

Which GPUs can run Jiutian?

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

306 cards match

Calculating

					Needs	Quantisation	Fit
244 tok/s 146–390 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	15.6 GB	Q8_0	Comfortable
244 tok/s 146–390 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	15.6 GB	Q8_0	Comfortable
195 tok/s 117–311 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	15.6 GB	Q8_0	Comfortable
195 tok/s 117–311 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	15.6 GB	Q8_0	Comfortable
156 tok/s 93–249 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	15.6 GB	Q8_0	Comfortable
149 tok/s 89–238 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	15.6 GB	Q8_0	Comfortable
149 tok/s 89–238 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	15.6 GB	Q8_0	Comfortable
143 tok/s 86–228 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	15.6 GB	Q8_0	Comfortable
127 tok/s 76–202 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	15.6 GB	Q8_0	Comfortable
127 tok/s 76–202 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	15.6 GB	Q8_0	Comfortable
127 tok/s 76–202 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	15.6 GB	Q8_0	Comfortable
120 tok/s 72–192 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	15.6 GB	Q8_0	Comfortable
117 tok/s 70–187 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.3 GB	IQ4_XS	Tight
102 tok/s 61–164 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	15.6 GB	Q8_0	Comfortable
102 tok/s 61–164 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	15.6 GB	Q8_0	Comfortable
102 tok/s 61–164 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	15.6 GB	Q8_0	Comfortable
102 tok/s 61–164 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	15.6 GB	Q8_0	Comfortable
102 tok/s 61–164 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	15.6 GB	Q8_0	Comfortable
78.0 tok/s 47–125 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	15.6 GB	Q8_0	Comfortable
78.0 tok/s 47–125 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	15.6 GB	Q8_0	Comfortable
65.0 tok/s 39–104 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	15.6 GB	Q8_0	Comfortable
63.6 tok/s 38–102 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	15.6 GB	Q8_0	Comfortable
62.2 tok/s 37–99 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	15.6 GB	Q8_0	Comfortable
62.2 tok/s 37–99 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	15.6 GB	Q8_0	Comfortable
62.2 tok/s 37–99 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	15.6 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: China Mobile
Organisation type: Industry
Country: China
Published: 12 October 2023

What it does

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

Domain: Language
Task: Language modeling/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: 13.9B
Training data: 2,000,000,000,000 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: 1.7 × 10²³ 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.

Likely above 10²³ FLOP: Yes
Record confidence: Likely

Sources

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

Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Jiutian

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 Jiutian

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

The hardware side

Minimum card

P102-101

Memory needed

8.3 GB

Fastest

244 tok/s

Jiutian is small enough at 13.9B parameters that hardware is rarely the obstacle — 306 of the cards we track can run it, including cards several years old.

At the low end, a P102-101 handles it — 10 GB, at IQ4_XS, for about 20.4 tokens per second.

At the other end, a B200 generates roughly 244 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Background

Jiutian was published by China Mobile, in China, in October 2023. industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation.

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

Reading the throughput figures

Across every card that can run it, the middle of the range is about 20.5 tokens per second, and 268 of them clear the ten tokens per second that roughly matches reading speed.

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.

What went into building it

Producing it required around 1.7 × 10²³ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Around 2,000,000,000,000 tokens went into training it.

Step by step

How to choose a GPU for Jiutian

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

01

Start from the memory column

Look at what Jiutian actually needs — around 8.3 GB at IQ4_XS. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Jiutian.
03

Choose how far you will compress it

Compression is what makes Jiutian fit smaller cards, at some cost in accuracy — IQ4_XS on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Sort by speed

The speed ordering for Jiutian is effectively an ordering by memory bandwidth, which is why the B200 tops it at 244 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage Jiutian from those with room to spare. Buy for the second if the context might grow.
06

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Jiutian.

Answers

Jiutian — common questions

Would two GPUs run Jiutian faster?

A second card roughly doubles the memory available but not the generation rate. With 306 cards already able to run Jiutian alone, the case for pairing is weak.

Why does the quantisation differ between cards for Jiutian?

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

How accurate are these Jiutian 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 146–390 tok/s on the B200 rather than a single number.

What GPU do I need to run Jiutian?

The smallest card in our catalogue that holds Jiutian is the P102-101, with 10 GB of memory. It runs the model at IQ4_XS using about 8.3 GB, and produces roughly 20.4 tokens per second. 306 cards in total can run it.

How fast is Jiutian on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 244 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 268 of the cards that can run Jiutian clear that.

How much VRAM does Jiutian need?

About 8.3 GB at IQ4_XS 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 Jiutian on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q5_K_M, using about 10.7 GB and generating roughly 49.7 tokens per second — a tight fit.

Can I run Jiutian on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 12.3 GB and generating roughly 50.0 tokens per second — a tight fit.

Can I run Jiutian on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 15.6 GB and generating roughly 40.8 tokens per second — a comfortable fit.

Is Jiutian open source?

Its weights are published, so Jiutian 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.

How many parameters does Jiutian have?

Jiutian has 13.9B parameters. A 13.9B parameter model is mentioned prominently at https://jiutian.10086.cn/portal/#/home 2025-01-13. 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 Jiutian?

Jiutian was published by China Mobile, based in China, categorised as industry.

When was Jiutian released?

Jiutian was published in October 2023. 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 Jiutian used for?

Jiutian works in Language, and is recorded as handling language modeling/generation. 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.

Where can I download Jiutian?

The weights for Jiutian 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 Jiutian?

Around 1.7 × 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.

Can I run Jiutian if it does not fit in my GPU?

It can be split between the card and system memory, but Jiutian generates painfully slowly that way — the nearest miss we calculate is short by 1.9 GB. Nothing on this page assumes offloading.

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