Japanese dialog transformers TPS calculator

Open weights NTT Communication Science Laboratories 1.6B parameters November 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 · Q8_0 · 23.0 tok/s

Fastest card

B200

2,118 tok/s · 180 GB

Which GPUs can run Japanese dialog transformers?

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
2,118 tok/s 1,271–3,388 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	2.4 GB	Q8_0	Comfortable
2,118 tok/s 1,271–3,388 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	2.4 GB	Q8_0	Comfortable
1,691 tok/s 1,015–2,706 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	2.4 GB	Q8_0	Comfortable
1,691 tok/s 1,015–2,706 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	2.4 GB	Q8_0	Comfortable
1,352 tok/s 811–2,164 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	2.4 GB	Q8_0	Comfortable
1,294 tok/s 777–2,071 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.4 GB	Q8_0	Comfortable
1,294 tok/s 777–2,071 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.4 GB	Q8_0	Comfortable
1,239 tok/s 743–1,982 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	2.4 GB	Q8_0	Comfortable
1,099 tok/s 660–1,759 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	2.4 GB	Q8_0	Comfortable
1,099 tok/s 660–1,759 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	2.4 GB	Q8_0	Comfortable
1,099 tok/s 660–1,759 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	2.4 GB	Q8_0	Comfortable
1,043 tok/s 626–1,669 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	2.4 GB	Q8_0	Comfortable
889 tok/s 534–1,423 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.4 GB	Q8_0	Comfortable
889 tok/s 534–1,423 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	2.4 GB	Q8_0	Comfortable
889 tok/s 534–1,423 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	2.4 GB	Q8_0	Comfortable
889 tok/s 534–1,423 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.4 GB	Q8_0	Comfortable
889 tok/s 534–1,423 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	2.4 GB	Q8_0	Comfortable
677 tok/s 406–1,084 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	2.4 GB	Q8_0	Comfortable
677 tok/s 406–1,084 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	2.4 GB	Q8_0	Comfortable
564 tok/s 339–903 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	2.4 GB	Q8_0	Comfortable
552 tok/s 331–884 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	2.4 GB	Q8_0	Comfortable
540 tok/s 324–864 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	2.4 GB	Q8_0	Comfortable
540 tok/s 324–864 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	2.4 GB	Q8_0	Comfortable
540 tok/s 324–864 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	2.4 GB	Q8_0	Comfortable
540 tok/s 324–864 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	2.4 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: NTT Communication Science Laboratories
Organisation type: Industry
Country: Japan
Published: 9 November 2021
Authors: Hiroaki Sugiyama, Masahiro Mizukami, Tsunehiro Arimoto, Hiromi Narimatsu, Yuya Chiba, Hideharu Nakajima, Toyomi Meguro

What it does

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

Domain: Language
Task: Chat, 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: 1.6B
Training data: 42,630,000,000 tokens

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 (non-commercial)
Training code: Open (non-commercial)

How it is classified

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

Citations: 59

Sources

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

Reference: Empirical Analysis of Training Strategies of Transformer-based Japanese Chit-chat Systems
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Japanese dialog transformers

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 Japanese dialog transformers

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

What you need to run it

Minimum card

Tesla C1080

Memory needed

2.4 GB

Fastest

2,118 tok/s

Japanese dialog transformers is small enough at 1.6B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla C1080. Its 4 GB is enough at Q8_0 compression, giving roughly 23.0 tokens per second.

At the other end, a B200 generates roughly 2,118 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

About this model

Japanese dialog transformers was published by NTT Communication Science Laboratories, in Japan, in November 2021. The organisation is categorised as industry.

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

How fast it runs, and why

Half the cards that hold it manage more than 59.5 tokens per second, and 794 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.

What went into building it

It was trained on about 42,630,000,000 tokens of text.

Step by step

How to choose a GPU for Japanese dialog transformers

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

01

Check what it needs before anything else

The table lists every card that can hold Japanese dialog transformers — around 2.4 GB at Q8_0. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

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

Set a quality floor

Compression is what makes Japanese dialog transformers fit smaller cards, at some cost in accuracy — Q8_0 on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Sort by speed

The speed ordering for Japanese dialog transformers is effectively an ordering by memory bandwidth, which is why the B200 tops it at 2,118 tok/s.
05

Look at the headroom, not just the fit

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

Answers

Japanese dialog transformers — common questions

Who created Japanese dialog transformers?

Japanese dialog transformers was published by NTT Communication Science Laboratories, based in Japan, categorised as industry.

When was Japanese dialog transformers released?

Japanese dialog transformers was published in November 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 Japanese dialog transformers used for?

Japanese dialog transformers works in Language, and is recorded as handling chat, Language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Japanese dialog transformers?

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

Can I run Japanese dialog transformers if it does not fit in my GPU?

It can be split between the card and system memory, but Japanese dialog transformers generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run Japanese dialog transformers faster?

Two cards buy memory rather than speed. That matters for Japanese dialog transformers only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for Japanese dialog transformers?

Because capacity varies, so does how hard Japanese dialog transformers has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Japanese dialog transformers speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 1,271–3,388 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 Japanese dialog transformers?

The smallest card in our catalogue that holds Japanese dialog transformers is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 2.4 GB, and produces roughly 23.0 tokens per second. 818 cards in total can run it.

How fast is Japanese dialog transformers on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 2,118 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 794 of the cards that can run Japanese dialog transformers clear that.

How much VRAM does Japanese dialog transformers need?

About 2.4 GB at Q8_0 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 Japanese dialog transformers on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 2.4 GB and generating roughly 394 tokens per second — a comfortable fit.

Can I run Japanese dialog transformers on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 2.4 GB and generating roughly 242 tokens per second — a comfortable fit.

Can I run Japanese dialog transformers on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 2.4 GB and generating roughly 299 tokens per second — a comfortable fit.

Can I run Japanese dialog transformers on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 2.4 GB and generating roughly 355 tokens per second — a comfortable fit.

Is Japanese dialog transformers open source?

Its weights are published, so Japanese dialog transformers 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 Japanese dialog transformers have?

Japanese dialog transformers has 1.6B parameters. "We examined the improvement in model size in detail by considering four model sizes: 0.35B, 0.7B, 1.1B, and 1.6B 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.

Source

Original publication

Record last updated 25 May 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.

All AI models