GPT-Neo-2.7B TPS calculator

Open weights EleutherAI 2.7B parameters March 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 · 13.7 tok/s

Fastest card

B200

1,255 tok/s · 180 GB

Which GPUs can run GPT-Neo-2.7B?

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: EleutherAI
Organisation type: Research collective
Country: United States of America
Published: 21 March 2021
Authors: Sid Black, Leo Gao, Phil Wang, Connor Leahy, Stella Biderman

What it does

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

Domain: Language
Task: Language modeling/generation, Question answering
Approach: Self-supervised learning

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: 420,000,000,000 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: 7.9 × 10²¹ FLOP
How it was established: Third-party estimation,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: Open source
Hugging Face: EleutherAI

How it is classified

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

Foundation model: Yes
Record confidence: Confident
Citations: 880
Benchmark data: GPT-Neo-2.7B

Sources

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

Reference: GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow
Last updated: 1 January 2026

The extremes

The ten fastest GPUs that run GPT-Neo-2.7B

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-Neo-2.7B

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

Tesla C1080

Memory needed

3.6 GB

Fastest

1,255 tok/s

GPT-Neo-2.7B 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.

At the low end, a Tesla C1080 handles it — 4 GB, at Q8_0, for about 13.7 tokens per second.

The quickest result comes from a B200 at around 1,255 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Where it came from

GPT-Neo-2.7B was published by EleutherAI, in United States of America, in March 2021. research collective is the category the publisher falls under.

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

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the EleutherAI organisation on Hugging Face.

Understanding the speeds

Across every card that can run it, the middle of the range is about 35.2 tokens per second, and 775 of them clear the ten tokens per second that roughly matches reading speed.

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.

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.

How it was trained

The training run consumed about 7.9 × 10²¹ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The training set ran to roughly 420,000,000,000 tokens.

Step by step

How to choose a GPU for GPT-Neo-2.7B

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

Look at what GPT-Neo-2.7B actually needs — around 3.6 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Match the context to your actual use

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for GPT-Neo-2.7B.
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-Neo-2.7B — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Compare tokens per second, not specifications

Sort by speed to see how cards rank for GPT-Neo-2.7B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 1,255 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage GPT-Neo-2.7B 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 GPT-Neo-2.7B.

Answers

GPT-Neo-2.7B — common questions

Where can I download GPT-Neo-2.7B?

Its weights are published under the EleutherAI organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

How much compute was used to train GPT-Neo-2.7B?

Around 7.9 × 10²¹ 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 GPT-Neo-2.7B if it does not fit in my GPU?

It can be split between the card and system memory, but GPT-Neo-2.7B generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run GPT-Neo-2.7B faster?

Two cards buy memory rather than speed. That matters for GPT-Neo-2.7B only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for GPT-Neo-2.7B?

Each card is shown running the least-compressed copy it can hold, and GPT-Neo-2.7B appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these GPT-Neo-2.7B 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 753–2,008 tok/s on the B200 rather than a single number.

What GPU do I need to run GPT-Neo-2.7B?

The smallest card in our catalogue that holds GPT-Neo-2.7B 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-Neo-2.7B 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-Neo-2.7B clear that.

How much VRAM does GPT-Neo-2.7B 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-Neo-2.7B 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-Neo-2.7B 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-Neo-2.7B 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-Neo-2.7B 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-Neo-2.7B open source?

Its weights are published, so GPT-Neo-2.7B 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-Neo-2.7B have?

GPT-Neo-2.7B has 2.7B parameters. source: https://www.eleuther.ai/projects/gpt-neo/ Note: Directory of LLMs (https://docs.google.com/spreadsheets/d/1gc6yse74XCwBx028HV_cvdxwXkmXejVjkO-Mz2uwE0k/edit#gid=0) gives a somewhat lower estimate (2e9). 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-Neo-2.7B?

GPT-Neo-2.7B was published by EleutherAI, based in United States of America, categorised as research collective.

When was GPT-Neo-2.7B released?

GPT-Neo-2.7B was published in March 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 GPT-Neo-2.7B used for?

GPT-Neo-2.7B works in Language, and is recorded as handling language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Source

Original publication

Record last updated 1 January 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