bilingual-gpt-neox-4b TPS calculator

Open weights rinna 3.8B parameters July 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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q5_K_M · 17.3 tok/s

Fastest card

B200

892 tok/s · 180 GB

Which GPUs can run bilingual-gpt-neox-4b?

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
892 tok/s 535–1,427 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	4.8 GB	Q8_0	Comfortable
892 tok/s 535–1,427 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	4.8 GB	Q8_0	Comfortable
712 tok/s 427–1,139 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	4.8 GB	Q8_0	Comfortable
712 tok/s 427–1,139 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	4.8 GB	Q8_0	Comfortable
569 tok/s 342–911 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	4.8 GB	Q8_0	Comfortable
545 tok/s 327–872 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	4.8 GB	Q8_0	Comfortable
545 tok/s 327–872 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	4.8 GB	Q8_0	Comfortable
522 tok/s 313–835 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	4.8 GB	Q8_0	Comfortable
463 tok/s 278–741 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	4.8 GB	Q8_0	Comfortable
463 tok/s 278–741 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	4.8 GB	Q8_0	Comfortable
463 tok/s 278–741 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	4.8 GB	Q8_0	Comfortable
439 tok/s 263–703 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	4.8 GB	Q8_0	Comfortable
374 tok/s 225–599 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	4.8 GB	Q8_0	Comfortable
374 tok/s 225–599 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	4.8 GB	Q8_0	Comfortable
374 tok/s 225–599 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	4.8 GB	Q8_0	Comfortable
374 tok/s 225–599 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	4.8 GB	Q8_0	Comfortable
374 tok/s 225–599 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	4.8 GB	Q8_0	Comfortable
285 tok/s 171–456 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	4.8 GB	Q8_0	Comfortable
285 tok/s 171–456 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	4.8 GB	Q8_0	Comfortable
238 tok/s 143–380 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	4.8 GB	Q8_0	Comfortable
233 tok/s 140–372 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	4.8 GB	Q8_0	Comfortable
227 tok/s 136–364 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	4.8 GB	Q8_0	Comfortable
227 tok/s 136–364 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	4.8 GB	Q8_0	Comfortable
227 tok/s 136–364 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	4.8 GB	Q8_0	Comfortable
227 tok/s 136–364 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	4.8 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: rinna
Organisation type: Industry
Country: Japan
Published: 31 July 2023
Authors: Tianyu Zhao, Toshiaki Wakatsuki, Akio Kaga, Koh Mitsuda, Kei Sawada

What it does

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

Domain: Language
Task: Language generation, Translation

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: 3.8B
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: 1.2 × 10²² 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.

Record confidence: Likely

Sources

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

Reference: Release of Pre-Trained Models for the Japanese Language
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run bilingual-gpt-neox-4b

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 bilingual-gpt-neox-4b

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

892 tok/s

bilingual-gpt-neox-4b is small enough at 3.8B 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, Q5_K_M compression, roughly 17.3 tokens per second.

Top of the range is the B200, at roughly 892 tokens per second thanks to 8,000 GB/s of bandwidth.

Where it came from

bilingual-gpt-neox-4b was published by rinna, in Japan, in July 2023. industry is the category the publisher falls under.

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

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

Understanding the speeds

The median result is around 29.9 tokens per second; 777 cards produce text faster than most people read it.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

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 1.2 × 10²² FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Step by step

How to choose a GPU for bilingual-gpt-neox-4b

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

Every card here has been checked against bilingual-gpt-neox-4b — around 3.4 GB at Q5_K_M. Capacity is the gate — a card either holds it or it does not.
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 bilingual-gpt-neox-4b stops fitting a card that seemed fine.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy of bilingual-gpt-neox-4b — Q5_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Compare tokens per second, not specifications

Ranking by tokens per second for bilingual-gpt-neox-4b follows memory bandwidth, not core counts, which is why the B200 tops it at 892 tok/s.
05

Check the fit verdict before buying

A tight fit runs bilingual-gpt-neox-4b but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
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 bilingual-gpt-neox-4b.

Answers

bilingual-gpt-neox-4b — common questions

Who created bilingual-gpt-neox-4b?

bilingual-gpt-neox-4b was published by rinna, based in Japan, categorised as industry.

When was bilingual-gpt-neox-4b released?

bilingual-gpt-neox-4b was published in July 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 bilingual-gpt-neox-4b used for?

bilingual-gpt-neox-4b works in Language, and is recorded as handling language generation, Translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download bilingual-gpt-neox-4b?

The weights for bilingual-gpt-neox-4b 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 bilingual-gpt-neox-4b?

Around 1.2 × 10²² 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 bilingual-gpt-neox-4b 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 bilingual-gpt-neox-4b assume it is fully resident.

Would two GPUs run bilingual-gpt-neox-4b faster?

Two cards buy memory rather than speed. That matters for bilingual-gpt-neox-4b only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for bilingual-gpt-neox-4b?

A larger card holds a more accurate copy. Across the cards that run bilingual-gpt-neox-4b, 3 compression levels are used; the floor control above pins it to one.

How accurate are these bilingual-gpt-neox-4b speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 535–1,427 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 bilingual-gpt-neox-4b?

The smallest card in our catalogue that holds bilingual-gpt-neox-4b is the Tesla C1080, with 4 GB of memory. It runs the model at Q5_K_M using about 3.4 GB, and produces roughly 17.3 tokens per second. 818 cards in total can run it.

How fast is bilingual-gpt-neox-4b on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 892 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 777 of the cards that can run bilingual-gpt-neox-4b clear that.

How much VRAM does bilingual-gpt-neox-4b need?

About 3.4 GB at Q5_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.

Can I run bilingual-gpt-neox-4b on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 4.8 GB and generating roughly 166 tokens per second — a comfortable fit.

Can I run bilingual-gpt-neox-4b on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 4.8 GB and generating roughly 102 tokens per second — a comfortable fit.

Can I run bilingual-gpt-neox-4b on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 4.8 GB and generating roughly 126 tokens per second — a comfortable fit.

Can I run bilingual-gpt-neox-4b on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 4.8 GB and generating roughly 149 tokens per second — a comfortable fit.

Is bilingual-gpt-neox-4b open source?

Its weights are published, so bilingual-gpt-neox-4b 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 bilingual-gpt-neox-4b have?

bilingual-gpt-neox-4b has 3.8B parameters. 3.8 billion. 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 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