TrellisNet-MoS (1.4x larger) PTB TPS calculator

Open weights Carnegie Mellon University (CMU),Intel Labs,Bosch Center for Artificial Intelligence 34M parameters October 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 · 1,084 tok/s

Fastest card

B200

99,654 tok/s · 180 GB

Which GPUs can run TrellisNet-MoS (1.4x larger) PTB?

Set the inputs, read the answer

A longer conversation needs more memory, which can push this model off smaller cards.

Hides cards that would only fit the model by compressing it below this point.

818 cards match

Calculating
Needs Quantisation Fit
99,654 tok/s

59,792–159,446 · low confidence

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 0.7 GB Q8_0 Comfortable
99,654 tok/s

59,792–159,446 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 0.7 GB Q8_0 Comfortable
79,576 tok/s

47,746–127,322 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 0.7 GB Q8_0 Comfortable
79,576 tok/s

47,746–127,322 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 0.7 GB Q8_0 Comfortable
63,642 tok/s

38,185–101,826 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 0.7 GB Q8_0 Comfortable
60,913 tok/s

36,548–97,462 · low confidence

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 0.7 GB Q8_0 Comfortable
60,913 tok/s

36,548–97,462 · low confidence

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 0.7 GB Q8_0 Comfortable
58,298 tok/s

34,979–93,276 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 0.7 GB Q8_0 Comfortable
51,739 tok/s

31,043–82,783 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 0.7 GB Q8_0 Comfortable
51,739 tok/s

31,043–82,783 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 0.7 GB Q8_0 Comfortable
51,739 tok/s

31,043–82,783 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 0.7 GB Q8_0 Comfortable
49,080 tok/s

29,448–78,527 · low confidence

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 0.7 GB Q8_0 Comfortable
41,855 tok/s

25,113–66,967 · low confidence

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 0.7 GB Q8_0 Comfortable
41,855 tok/s

25,113–66,967 · low confidence

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 0.7 GB Q8_0 Comfortable
41,855 tok/s

25,113–66,967 · low confidence

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 0.7 GB Q8_0 Comfortable
41,855 tok/s

25,113–66,967 · low confidence

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 0.7 GB Q8_0 Comfortable
41,855 tok/s

25,113–66,967 · low confidence

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 0.7 GB Q8_0 Comfortable
31,869 tok/s

19,122–50,991 · low confidence

Radeon Instinct MI250 AMD 128 GB 3,280 GB/s Nov 2021 0.7 GB Q8_0 Comfortable
31,869 tok/s

19,122–50,991 · low confidence

Radeon Instinct MI250X AMD 128 GB 3,280 GB/s Nov 2021 0.7 GB Q8_0 Comfortable
26,558 tok/s

15,935–42,492 · low confidence

Data Center GPU Max 1550 Intel 128 GB 3,280 GB/s Jan 2023 0.7 GB Q8_0 Comfortable
25,991 tok/s

15,595–41,586 · low confidence

Data Center GPU Max Subsystem Intel 128 GB 3,210 GB/s Jan 2023 0.7 GB Q8_0 Comfortable
25,412 tok/s

15,247–40,659 · low confidence

A100 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Nov 2020 0.7 GB Q8_0 Comfortable
25,412 tok/s

15,247–40,659 · low confidence

A100X NVIDIA 80 GB 2,040 GB/s Jun 2021 0.7 GB Q8_0 Comfortable
25,412 tok/s

15,247–40,659 · low confidence

A800 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Aug 2022 0.7 GB Q8_0 Comfortable
25,412 tok/s

15,247–40,659 · 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),Intel Labs,Bosch Center for Artificial Intelligence
Organisation type
Academia,Industry,Industry
Country
United States of America, Germany
Published
15 October 2018
Authors
Shaojie Bai, J. Zico Kolter, Vladlen Koltun

What it does

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

Domain
Language
Task
Language modeling

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
34M

34M, table 1

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 (unrestricted)
Training code
Open source

MIT license for code. Weights available for PTB: https://github.com/locuslab/trellisnet/blob/master/README.md

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
164
Benchmark data
TrellisNet-MoS (1.4x larger)

Sources

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

Reference
Trellis Networks for Sequence Modeling
Last updated
25 May 2026

The extremes

What the numbers mean

What you need to run it

Minimum card

Tesla C1080

Memory needed

0.7 GB

Fastest

99,654 tok/s

TrellisNet-MoS (1.4x larger) PTB is small enough at 34M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla C1080. Its 4 GB is enough at Q8_0 compression, giving roughly 1,084 tokens per second.

Top of the range is the B200, at roughly 99,654 tokens per second thanks to 8,000 GB/s of bandwidth.

Background

TrellisNet-MoS (1.4x larger) PTB was published by Carnegie Mellon University (CMU),Intel Labs,Bosch Center for Artificial Intelligence, in United States of America, in October 2018. The organisation is categorised as academia,Industry,Industry.

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

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 2,798.3 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.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

Step by step

How to choose a GPU for TrellisNet-MoS (1.4x larger) PTB

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

  1. 01

    Start from the memory column

    Every card here has been checked against TrellisNet-MoS (1.4x larger) PTB — around 0.7 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.

  2. 02

    Match the context to your actual use

    The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context TrellisNet-MoS (1.4x larger) PTB can slip off a card that handles short questions easily.

  3. 03

    Decide how much compression you will accept

    Compression is what makes TrellisNet-MoS (1.4x larger) 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.

  4. 04

    Compare tokens per second, not specifications

    Sort by speed to see how cards rank for TrellisNet-MoS (1.4x larger) PTB. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 99,654 tok/s.

  5. 05

    Check the fit verdict before buying

    A tight fit runs TrellisNet-MoS (1.4x larger) PTB but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.

  6. 06

    Open the card you have settled on

    Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for TrellisNet-MoS (1.4x larger) PTB alone — a card is usually bought for more than one model.

Answers

TrellisNet-MoS (1.4x larger) PTB — common questions

01

Where can I download TrellisNet-MoS (1.4x larger) PTB?

The weights for TrellisNet-MoS (1.4x larger) PTB are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

02

Can I run TrellisNet-MoS (1.4x larger) 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 TrellisNet-MoS (1.4x larger) PTB is rarely worth using. Every figure here assumes the whole model is on the card.

03

Would two GPUs run TrellisNet-MoS (1.4x larger) PTB faster?

Two cards buy memory rather than speed. That matters for TrellisNet-MoS (1.4x larger) PTB only if one card cannot hold it — 818 can, so a second adds little.

04

Why does the quantisation differ between cards for TrellisNet-MoS (1.4x larger) PTB?

A larger card holds a more accurate copy. Across the cards that run TrellisNet-MoS (1.4x larger) PTB, 1 compression levels are used; the floor control above pins it to one.

05

How accurate are these TrellisNet-MoS (1.4x larger) PTB speed estimates?

These are estimates with real error bars. The fastest result here, 59,792–159,446 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

06

What GPU do I need to run TrellisNet-MoS (1.4x larger) PTB?

The smallest card in our catalogue that holds TrellisNet-MoS (1.4x larger) 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 1,084 tokens per second. 818 cards in total can run it.

07

How fast is TrellisNet-MoS (1.4x larger) PTB on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 99,654 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 TrellisNet-MoS (1.4x larger) PTB clear that.

08

How much VRAM does TrellisNet-MoS (1.4x larger) 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.

09

Can I run TrellisNet-MoS (1.4x larger) 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 18,561 tokens per second — a comfortable fit.

10

Can I run TrellisNet-MoS (1.4x larger) 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 11,366 tokens per second — a comfortable fit.

11

Can I run TrellisNet-MoS (1.4x larger) 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 14,076 tokens per second — a comfortable fit.

12

Can I run TrellisNet-MoS (1.4x larger) 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 16,692 tokens per second — a comfortable fit.

13

Is TrellisNet-MoS (1.4x larger) PTB open source?

Its weights are published, so TrellisNet-MoS (1.4x larger) 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.

14

How many parameters does TrellisNet-MoS (1.4x larger) PTB have?

TrellisNet-MoS (1.4x larger) PTB has 34M parameters. 34M, table 1. 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.

15

Who created TrellisNet-MoS (1.4x larger) PTB?

TrellisNet-MoS (1.4x larger) PTB was published by Carnegie Mellon University (CMU),Intel Labs,Bosch Center for Artificial Intelligence, based in United States of America, categorised as academia,Industry,Industry.

16

When was TrellisNet-MoS (1.4x larger) PTB released?

TrellisNet-MoS (1.4x larger) PTB was published in October 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.

17

What is TrellisNet-MoS (1.4x larger) PTB used for?

TrellisNet-MoS (1.4x larger) PTB works in Language, and is recorded as handling language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

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.