L_UL-seq TPS calculator

Open weights New York University (NYU),Facebook AI Research,CIFAR AI Research 247M parameters August 2019

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 · 149 tok/s

Fastest card

B200

13,718 tok/s · 180 GB

Which GPUs can run L_UL-seq?

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
13,718 tok/s 8,231–21,948 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.0 GB	Q8_0	Comfortable
13,718 tok/s 8,231–21,948 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.0 GB	Q8_0	Comfortable
10,954 tok/s 6,572–17,526 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.0 GB	Q8_0	Comfortable
10,954 tok/s 6,572–17,526 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.0 GB	Q8_0	Comfortable
8,760 tok/s 5,256–14,017 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.0 GB	Q8_0	Comfortable
8,385 tok/s 5,031–13,416 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.0 GB	Q8_0	Comfortable
8,385 tok/s 5,031–13,416 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.0 GB	Q8_0	Comfortable
8,025 tok/s 4,815–12,840 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.0 GB	Q8_0	Comfortable
7,122 tok/s 4,273–11,395 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.0 GB	Q8_0	Comfortable
7,122 tok/s 4,273–11,395 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.0 GB	Q8_0	Comfortable
7,122 tok/s 4,273–11,395 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.0 GB	Q8_0	Comfortable
6,756 tok/s 4,054–10,809 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
5,761 tok/s 3,457–9,218 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
5,761 tok/s 3,457–9,218 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.0 GB	Q8_0	Comfortable
5,761 tok/s 3,457–9,218 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
5,761 tok/s 3,457–9,218 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
5,761 tok/s 3,457–9,218 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
4,387 tok/s 2,632–7,019 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.0 GB	Q8_0	Comfortable
4,387 tok/s 2,632–7,019 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.0 GB	Q8_0	Comfortable
3,656 tok/s 2,193–5,849 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.0 GB	Q8_0	Comfortable
3,578 tok/s 2,147–5,724 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.0 GB	Q8_0	Comfortable
3,498 tok/s 2,099–5,597 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.0 GB	Q8_0	Comfortable
3,498 tok/s 2,099–5,597 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.0 GB	Q8_0	Comfortable
3,498 tok/s 2,099–5,597 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.0 GB	Q8_0	Comfortable
3,498 tok/s 2,099–5,597 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.0 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: New York University (NYU),Facebook AI Research,CIFAR AI Research
Organisation type: Academia,Industry,Research collective
Country: United States of America, France, Canada
Published: 12 August 2019
Authors: Sean Welleck, Ilia Kulikov, Stephen Roller, Emily Dinan, Kyunghyun Cho, Jason Weston

What it does

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

Domain: Language
Task: Language modeling/generation

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: 247M
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 (non-commercial)
Training code: Open (non-commercial)

How it is classified

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

Citations: 690
Benchmark data: L_UL-seq

Sources

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

Reference: Neural Text Generation with Unlikelihood Training
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run L_UL-seq

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 L_UL-seq

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

1.0 GB

Fastest

13,718 tok/s

L_UL-seq is small enough at 247M 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 149 tokens per second.

Top of the range is the B200, at roughly 13,718 tokens per second thanks to 8,000 GB/s of bandwidth.

Background

L_UL-seq was published by New York University (NYU),Facebook AI Research,CIFAR AI Research, in United States of America, in August 2019. academia,Industry,Research collective is the category the publisher falls under.

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

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all.

Reading the throughput figures

Half the cards that hold it manage more than 385.2 tokens per second, and 818 exceed reading speed outright.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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 L_UL-seq

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 L_UL-seq actually needs — around 1.0 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 L_UL-seq.
03

Set a quality floor

Each card runs the least-compressed copy it can hold — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage L_UL-seq by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for L_UL-seq follows memory bandwidth, not core counts, which is why the B200 tops it at 13,718 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage L_UL-seq from those with room to spare. Buy for the second if the context might grow.
06

Check the card from the other side

Following a card through to its own page shows every other model it can hold, which is the question that follows once L_UL-seq is settled.

Answers

L_UL-seq — common questions

Why does the quantisation differ between cards for L_UL-seq?

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

How accurate are these L_UL-seq 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 8,231–21,948 tok/s on the B200 rather than a single number.

What GPU do I need to run L_UL-seq?

The smallest card in our catalogue that holds L_UL-seq is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.0 GB, and produces roughly 149 tokens per second. 818 cards in total can run it.

How fast is L_UL-seq on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 13,718 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 L_UL-seq clear that.

How much VRAM does L_UL-seq need?

About 1.0 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 L_UL-seq on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.0 GB and generating roughly 2,555 tokens per second — a comfortable fit.

Can I run L_UL-seq on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.0 GB and generating roughly 1,564 tokens per second — a comfortable fit.

Can I run L_UL-seq on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.0 GB and generating roughly 1,938 tokens per second — a comfortable fit.

Can I run L_UL-seq on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.0 GB and generating roughly 2,298 tokens per second — a comfortable fit.

Is L_UL-seq open source?

Its weights are published, so L_UL-seq 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 L_UL-seq have?

L_UL-seq has 247M 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 L_UL-seq?

L_UL-seq was published by New York University (NYU),Facebook AI Research,CIFAR AI Research, based in United States of America, categorised as academia,Industry,Research collective.

When was L_UL-seq released?

L_UL-seq was published in August 2019. 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 L_UL-seq used for?

L_UL-seq 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 L_UL-seq?

The weights for L_UL-seq 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 L_UL-seq 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 L_UL-seq assume it is fully resident.

Would two GPUs run L_UL-seq faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold L_UL-seq on their own, a second card is rarely the answer here.

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