GPT-NeoX-Japanese TPS calculator

Open weights Abeja 2.7B parameters July 2022

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 · 13.7 tok/s

Fastest card

B200

1,255 tok/s · 180 GB

Which GPUs can run GPT-NeoX-Japanese?

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
1,255 tok/s 753–2,008 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	3.6 GB	Q8_0	Comfortable
1,255 tok/s 753–2,008 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	3.6 GB	Q8_0	Comfortable
1,002 tok/s 601–1,603 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	3.6 GB	Q8_0	Comfortable
1,002 tok/s 601–1,603 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	3.6 GB	Q8_0	Comfortable
801 tok/s 481–1,282 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	3.6 GB	Q8_0	Comfortable
767 tok/s 460–1,227 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.6 GB	Q8_0	Comfortable
767 tok/s 460–1,227 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.6 GB	Q8_0	Comfortable
734 tok/s 440–1,175 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	3.6 GB	Q8_0	Comfortable
652 tok/s 391–1,042 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	3.6 GB	Q8_0	Comfortable
652 tok/s 391–1,042 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	3.6 GB	Q8_0	Comfortable
652 tok/s 391–1,042 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	3.6 GB	Q8_0	Comfortable
618 tok/s 371–989 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	3.6 GB	Q8_0	Comfortable
527 tok/s 316–843 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.6 GB	Q8_0	Comfortable
527 tok/s 316–843 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	3.6 GB	Q8_0	Comfortable
527 tok/s 316–843 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	3.6 GB	Q8_0	Comfortable
527 tok/s 316–843 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.6 GB	Q8_0	Comfortable
527 tok/s 316–843 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	3.6 GB	Q8_0	Comfortable
401 tok/s 241–642 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	3.6 GB	Q8_0	Comfortable
401 tok/s 241–642 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	3.6 GB	Q8_0	Comfortable
334 tok/s 201–535 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	3.6 GB	Q8_0	Comfortable
327 tok/s 196–524 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	3.6 GB	Q8_0	Comfortable
320 tok/s 192–512 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	3.6 GB	Q8_0	Comfortable
320 tok/s 192–512 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	3.6 GB	Q8_0	Comfortable
320 tok/s 192–512 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	3.6 GB	Q8_0	Comfortable
320 tok/s 192–512 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	3.6 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: Abeja
Organisation type: Industry
Country: Japan
Published: 27 July 2022
Authors: Shinya Otani, Takayoshi Makabe, Anuj Arora, Kyo Hattori

What it does

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

Domain: Language
Task: Language modeling/generation
Base model: GPT-NeoX-20B

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: 2.7B
Training data: 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 (unrestricted)

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: This repository provides a 2.7B-parameter Japanese GPT-NeoX-based model. The model was trained by ABEJA, Inc
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run GPT-NeoX-Japanese

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 GPT-NeoX-Japanese

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 it takes to run this model

Minimum card

Tesla C1080

Memory needed

3.6 GB

Fastest

1,255 tok/s

GPT-NeoX-Japanese is small enough at 2.7B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the Tesla C1080 with 4 GB, running it at Q8_0 and producing around 13.7 tokens per second.

Top of the range is the B200, at roughly 1,255 tokens per second thanks to 8,000 GB/s of bandwidth.

Background

GPT-NeoX-Japanese was published by Abeja, in Japan, in July 2022. It comes out of industry.

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

It builds on GPT-NeoX-20B, which is why it shares that model's general shape and size.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

Reading the throughput figures

Half the cards that hold it manage more than 35.2 tokens per second, and 775 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.

Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.

Step by step

How to choose a GPU for GPT-NeoX-Japanese

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

The table lists every card that can hold GPT-NeoX-Japanese — around 3.6 GB at Q8_0. That figure, not the card's headline performance, is what decides whether it runs.
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 GPT-NeoX-Japanese stops fitting a card that seemed fine.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of GPT-NeoX-Japanese — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

The speed ordering for GPT-NeoX-Japanese is effectively an ordering by memory bandwidth, which is why the B200 tops it at 1,255 tok/s.
05

Read the fit column last

Tight means GPT-NeoX-Japanese 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.
06

Check the card from the other side

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for GPT-NeoX-Japanese alone — a card is usually bought for more than one model.

Answers

GPT-NeoX-Japanese — common questions

Would two GPUs run GPT-NeoX-Japanese faster?

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

Why does the quantisation differ between cards for GPT-NeoX-Japanese?

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

How accurate are these GPT-NeoX-Japanese speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 753–2,008 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 GPT-NeoX-Japanese?

The smallest card in our catalogue that holds GPT-NeoX-Japanese is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 3.6 GB, and produces roughly 13.7 tokens per second. 818 cards in total can run it.

How fast is GPT-NeoX-Japanese on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,255 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 775 of the cards that can run GPT-NeoX-Japanese clear that.

How much VRAM does GPT-NeoX-Japanese need?

About 3.6 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 GPT-NeoX-Japanese on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 3.6 GB and generating roughly 234 tokens per second — a comfortable fit.

Can I run GPT-NeoX-Japanese on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 3.6 GB and generating roughly 143 tokens per second — a comfortable fit.

Can I run GPT-NeoX-Japanese on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 3.6 GB and generating roughly 177 tokens per second — a comfortable fit.

Can I run GPT-NeoX-Japanese on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 3.6 GB and generating roughly 210 tokens per second — a comfortable fit.

Is GPT-NeoX-Japanese open source?

Its weights are published, so GPT-NeoX-Japanese 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 GPT-NeoX-Japanese have?

GPT-NeoX-Japanese has 2.7B parameters. 2.7B. 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 GPT-NeoX-Japanese?

GPT-NeoX-Japanese was published by Abeja, based in Japan, categorised as industry.

When was GPT-NeoX-Japanese released?

GPT-NeoX-Japanese was published in July 2022. 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 GPT-NeoX-Japanese used for?

GPT-NeoX-Japanese 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 GPT-NeoX-Japanese?

The weights for GPT-NeoX-Japanese 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 GPT-NeoX-Japanese if it does not fit in my GPU?

It can be split between the card and system memory, but GPT-NeoX-Japanese generates painfully slowly that way. 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