DARTS (second order) (PTB) TPS calculator

Open weights Carnegie Mellon University (CMU),DeepMind 23M parameters June 2018

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 · 1,603 tok/s

Fastest card

B200

147,315 tok/s · 180 GB

Which GPUs can run DARTS (second order) (PTB)?

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
147,315 tok/s 88,389–235,703 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.7 GB	Q8_0	Comfortable
147,315 tok/s 88,389–235,703 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.7 GB	Q8_0	Comfortable
117,634 tok/s 70,581–188,215 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.7 GB	Q8_0	Comfortable
117,634 tok/s 70,581–188,215 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.7 GB	Q8_0	Comfortable
94,079 tok/s 56,447–150,526 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
90,046 tok/s 54,028–144,074 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.7 GB	Q8_0	Comfortable
90,046 tok/s 54,028–144,074 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.7 GB	Q8_0	Comfortable
86,179 tok/s 51,707–137,886 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.7 GB	Q8_0	Comfortable
76,484 tok/s 45,890–122,374 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
76,484 tok/s 45,890–122,374 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
76,484 tok/s 45,890–122,374 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.7 GB	Q8_0	Comfortable
72,552 tok/s 43,531–116,084 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
61,872 tok/s 37,123–98,995 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
61,872 tok/s 37,123–98,995 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.7 GB	Q8_0	Comfortable
61,872 tok/s 37,123–98,995 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
61,872 tok/s 37,123–98,995 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
61,872 tok/s 37,123–98,995 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.7 GB	Q8_0	Comfortable
47,111 tok/s 28,267–75,378 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.7 GB	Q8_0	Comfortable
47,111 tok/s 28,267–75,378 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.7 GB	Q8_0	Comfortable
39,259 tok/s 23,556–62,815 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
38,421 tok/s 23,053–61,474 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.7 GB	Q8_0	Comfortable
37,565 tok/s 22,539–60,104 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.7 GB	Q8_0	Comfortable
37,565 tok/s 22,539–60,104 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.7 GB	Q8_0	Comfortable
37,565 tok/s 22,539–60,104 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.7 GB	Q8_0	Comfortable
37,565 tok/s 22,539–60,104 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	0.7 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: Carnegie Mellon University (CMU),DeepMind
Organisation type: Academia,Industry
Country: United States of America, United Kingdom of Great Britain and Northern Ireland
Published: 24 June 2018
Authors: Hanxiao Liu, Karen Simonyan, Yiming Yang

What it does

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

Domain: Language
Task: Language modeling, Neural Architecture Search - NAS

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: 23M
Training data: 929,000 tokens
Epochs: 300

The training run

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

Chips used: 1
Wall-clock time: 24 hours

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.

Record confidence: Confident
Citations: 4,929
Benchmark data: DARTS (second order)

Sources

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

Reference: DARTS: Differentiable Architecture Search
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run DARTS (second order) (PTB)

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 DARTS (second order) (PTB)

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

0.7 GB

Fastest

147,315 tok/s

DARTS (second order) (PTB) is small enough at 23M 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 1,603 tokens per second.

The quickest result comes from a B200 at around 147,315 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Background

DARTS (second order) (PTB) was published by Carnegie Mellon University (CMU),DeepMind, in United States of America, in June 2018. It comes out of academia,Industry.

It works in Language, and is recorded as doing language modeling, Neural Architecture Search - NAS.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

Reading the throughput figures

Half the cards that hold it manage more than 4,136.6 tokens per second, and 818 exceed reading speed outright.

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.

What went into building it

It was trained on about 929,000 tokens of text.

Step by step

How to choose a GPU for DARTS (second order) (PTB)

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

01

Read the memory figure first

Look at what DARTS (second order) (PTB) actually needs — around 0.7 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for DARTS (second order) (PTB).
03

Choose how far you will compress it

Compression is what makes DARTS (second order) (PTB) 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 DARTS (second order) (PTB) is effectively an ordering by memory bandwidth, which is why the B200 tops it at 147,315 tok/s.
05

Read the fit column last

The fit column separates cards that just manage DARTS (second order) (PTB) from those with room to spare. Buy for the second if the context might grow.
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 DARTS (second order) (PTB) alone — a card is usually bought for more than one model.

Answers

DARTS (second order) (PTB) — common questions

Can I run DARTS (second order) (PTB) on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.7 GB and generating roughly 24,675 tokens per second — a comfortable fit.

Is DARTS (second order) (PTB) open source?

Its weights are published, so DARTS (second order) (PTB) 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 DARTS (second order) (PTB) have?

DARTS (second order) (PTB) has 23M 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 DARTS (second order) (PTB)?

DARTS (second order) (PTB) was published by Carnegie Mellon University (CMU),DeepMind, based in United States of America, categorised as academia,Industry.

When was DARTS (second order) (PTB) released?

DARTS (second order) (PTB) was published in June 2018. 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 DARTS (second order) (PTB) used for?

DARTS (second order) (PTB) works in Language, and is recorded as handling language modeling, Neural Architecture Search - NAS. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download DARTS (second order) (PTB)?

The weights for DARTS (second order) (PTB) 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 DARTS (second order) (PTB) if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded DARTS (second order) (PTB) is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run DARTS (second order) (PTB) faster?

Two cards buy memory rather than speed. That matters for DARTS (second order) (PTB) only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for DARTS (second order) (PTB)?

Because capacity varies, so does how hard DARTS (second order) (PTB) has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these DARTS (second order) (PTB) speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 88,389–235,703 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 DARTS (second order) (PTB)?

The smallest card in our catalogue that holds DARTS (second order) (PTB) is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.7 GB, and produces roughly 1,603 tokens per second. 818 cards in total can run it.

How fast is DARTS (second order) (PTB) on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 147,315 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 818 of the cards that can run DARTS (second order) (PTB) clear that.

How much VRAM does DARTS (second order) (PTB) need?

About 0.7 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 DARTS (second order) (PTB) on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.7 GB and generating roughly 27,437 tokens per second — a comfortable fit.

Can I run DARTS (second order) (PTB) on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.7 GB and generating roughly 16,801 tokens per second — a comfortable fit.

Can I run DARTS (second order) (PTB) on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.7 GB and generating roughly 20,808 tokens per second — a comfortable fit.

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