GPT-NeoX-20B TPS calculator

Open weights EleutherAI 20B parameters February 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

293 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Quadro K6000

12 GB · Q3_K_M · 14.0 tok/s

Fastest card

B200

169 tok/s · 180 GB

Which GPUs can run GPT-NeoX-20B?

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

293 cards match

Calculating

					Needs	Quantisation	Fit
169 tok/s 102–271 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	22.1 GB	Q8_0	Comfortable
169 tok/s 102–271 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	22.1 GB	Q8_0	Comfortable
135 tok/s 81–216 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	22.1 GB	Q8_0	Comfortable
135 tok/s 81–216 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	22.1 GB	Q8_0	Comfortable
108 tok/s 65–173 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	22.1 GB	Q8_0	Comfortable
104 tok/s 62–166 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	22.1 GB	Q8_0	Comfortable
104 tok/s 62–166 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	22.1 GB	Q8_0	Comfortable
99.1 tok/s 59–159 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	22.1 GB	Q8_0	Comfortable
88.0 tok/s 53–141 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	22.1 GB	Q8_0	Comfortable
88.0 tok/s 53–141 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	22.1 GB	Q8_0	Comfortable
88.0 tok/s 53–141 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	22.1 GB	Q8_0	Comfortable
83.4 tok/s 50–134 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	22.1 GB	Q8_0	Comfortable
71.2 tok/s 43–114 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	22.1 GB	Q8_0	Comfortable
71.2 tok/s 43–114 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	22.1 GB	Q8_0	Comfortable
71.2 tok/s 43–114 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	22.1 GB	Q8_0	Comfortable
71.2 tok/s 43–114 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	22.1 GB	Q8_0	Comfortable
71.2 tok/s 43–114 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	22.1 GB	Q8_0	Comfortable
55.2 tok/s 33–88 · low confidence	Tesla V100 SXM2 16 GB NVIDIA	16 GB	1,130 GB/s	Nov 2019	12.8 GB	Q4_K_M	Tight
54.2 tok/s 33–87 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	22.1 GB	Q8_0	Comfortable
54.2 tok/s 33–87 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	22.1 GB	Q8_0	Comfortable
52.1 tok/s 31–83 · low confidence	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	10.5 GB	Q3_K_M	Tight
52.1 tok/s 31–83 · low confidence	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	10.5 GB	Q3_K_M	Tight
46.9 tok/s 28–75 · low confidence	GeForce RTX 5080 NVIDIA	16 GB	960 GB/s	Jan 2025	12.8 GB	Q4_K_M	Tight
45.2 tok/s 27–72 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	22.1 GB	Q8_0	Comfortable
44.2 tok/s 27–71 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	22.1 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: EleutherAI
Organisation type: Research collective
Country: United States of America
Published: 9 February 2022
Authors: Sid Black, Stella Biderman, Eric Hallahan, Quentin Anthony, Leo Gao, Laurence Golding, Horace He, Connor Leahy, Kyle McDonell, Jason Phang, Michael Pieler, USVSN Sai Prashanth, Shivanshu Purohit, Laria Reynolds, Jonathan Tow, Ben Wang, Samuel Weinbach

What it does

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

Domain: Language
Task: Language modeling/generation
Approach: Self-supervised learning
Numerical format: FP16

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: 20B
Training data: 341,173,367,965 tokens
Epochs: 1.4
Batch size: 3,150,000

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: 9.3 × 10²² FLOP
How it was established: Hardware

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware: NVIDIA A100 SXM4 40 GB
Chips used: 96
Chip-hours: 207,360
Wall-clock time: 2,160 hours (90 days)
Power draw: 77.3 kW
Compute cost: $184,273

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: Open source

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
Citations: 998
Benchmark data: GPT-NeoX-20B

Sources

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

Reference: GPT-NeoX-20B: An Open-Source Autoregressive Language Model
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run GPT-NeoX-20B

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-20B

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

Quadro K6000

Memory needed

10.5 GB

Fastest

169 tok/s

With 20B parameters, GPT-NeoX-20B lands in the range a serious desktop card can handle once the weights are compressed. 293 of the cards we track can run it.

The least hardware that works is a Quadro K6000. Its 12 GB is enough at Q3_K_M compression, giving roughly 14.0 tokens per second.

At the other end, a B200 generates roughly 169 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Where it came from

GPT-NeoX-20B was published by EleutherAI, in United States of America, in February 2022. research collective is the category the publisher falls under.

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

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold.

Understanding the speeds

The median result is around 20.6 tokens per second; 248 cards produce text faster than most people read it.

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

Producing it required around 9.3 × 10²² FLOP of arithmetic, on NVIDIA A100 SXM4 40 GB, which is a statement about the training budget rather than about inference.

Around 341,173,367,965 tokens went into training it.

It is tracked in the underlying dataset for one reason in particular: historical significance.

Step by step

How to choose a GPU for GPT-NeoX-20B

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 GPT-NeoX-20B — around 10.5 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Decide how long your conversations run

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context GPT-NeoX-20B can slip off a card that handles short questions easily.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy of GPT-NeoX-20B — Q3_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

The speed ordering for GPT-NeoX-20B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 169 tok/s.
05

Look at the headroom, not just the fit

Tight means GPT-NeoX-20B 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

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 GPT-NeoX-20B.

Answers

GPT-NeoX-20B — common questions

How accurate are these GPT-NeoX-20B speed estimates?

These are estimates with real error bars. The fastest result here, 102–271 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run GPT-NeoX-20B?

The smallest card in our catalogue that holds GPT-NeoX-20B is the Quadro K6000, with 12 GB of memory. It runs the model at Q3_K_M using about 10.5 GB, and produces roughly 14.0 tokens per second. 293 cards in total can run it.

How fast is GPT-NeoX-20B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 169 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 248 of the cards that can run GPT-NeoX-20B clear that.

How much VRAM does GPT-NeoX-20B need?

About 10.5 GB at Q3_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 GPT-NeoX-20B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q3_K_M, using about 10.5 GB and generating roughly 52.1 tokens per second — a tight fit.

Can I run GPT-NeoX-20B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q4_K_M, using about 12.8 GB and generating roughly 55.2 tokens per second — a tight fit.

Can I run GPT-NeoX-20B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q6_K, using about 17.5 GB and generating roughly 41.2 tokens per second — a comfortable fit.

Is GPT-NeoX-20B open source?

Its weights are published, so GPT-NeoX-20B 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-20B have?

GPT-NeoX-20B has 20B 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 GPT-NeoX-20B?

GPT-NeoX-20B was published by EleutherAI, based in United States of America, categorised as research collective.

When was GPT-NeoX-20B released?

GPT-NeoX-20B was published in February 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-20B used for?

GPT-NeoX-20B works in Language, and is recorded as handling language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download GPT-NeoX-20B?

The weights for GPT-NeoX-20B 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 GPT-NeoX-20B?

Around 9.3 × 10²² FLOP, on NVIDIA A100 SXM4 40 GB. 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 GPT-NeoX-20B if it does not fit in my GPU?

It can be split between the card and system memory, but GPT-NeoX-20B generates painfully slowly that way — the nearest miss we calculate is short by 2.9 GB. Nothing on this page assumes offloading.

Would two GPUs run GPT-NeoX-20B faster?

Two cards buy memory rather than speed. That matters for GPT-NeoX-20B only if one card cannot hold it — 293 can, so a second adds little.

Why does the quantisation differ between cards for GPT-NeoX-20B?

Because capacity varies, so does how hard GPT-NeoX-20B has to be squeezed — 4 distinct levels appear in the table above. Set a minimum quality to compare at one.

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