Segatron XL base, M=384 TPS calculator

Open weights University of Waterloo,RSVP.ai,Peking University 257M parameters April 2020

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 · 143 tok/s

Fastest card

B200

13,184 tok/s · 180 GB

Which GPUs can run Segatron XL base, M=384?

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
13,184 tok/s 7,910–21,094 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.0 GB	Q8_0	Comfortable
13,184 tok/s 7,910–21,094 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.0 GB	Q8_0	Comfortable
10,528 tok/s 6,317–16,844 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.0 GB	Q8_0	Comfortable
10,528 tok/s 6,317–16,844 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.0 GB	Q8_0	Comfortable
8,420 tok/s 5,052–13,471 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.0 GB	Q8_0	Comfortable
8,059 tok/s 4,835–12,894 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.0 GB	Q8_0	Comfortable
8,059 tok/s 4,835–12,894 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.0 GB	Q8_0	Comfortable
7,713 tok/s 4,628–12,340 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.0 GB	Q8_0	Comfortable
6,845 tok/s 4,107–10,952 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.0 GB	Q8_0	Comfortable
6,845 tok/s 4,107–10,952 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.0 GB	Q8_0	Comfortable
6,845 tok/s 4,107–10,952 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.0 GB	Q8_0	Comfortable
6,493 tok/s 3,896–10,389 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
5,537 tok/s 3,322–8,860 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
5,537 tok/s 3,322–8,860 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.0 GB	Q8_0	Comfortable
5,537 tok/s 3,322–8,860 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
5,537 tok/s 3,322–8,860 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
5,537 tok/s 3,322–8,860 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
4,216 tok/s 2,530–6,746 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.0 GB	Q8_0	Comfortable
4,216 tok/s 2,530–6,746 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.0 GB	Q8_0	Comfortable
3,513 tok/s 2,108–5,622 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.0 GB	Q8_0	Comfortable
3,439 tok/s 2,063–5,502 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.0 GB	Q8_0	Comfortable
3,362 tok/s 2,017–5,379 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.0 GB	Q8_0	Comfortable
3,362 tok/s 2,017–5,379 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.0 GB	Q8_0	Comfortable
3,362 tok/s 2,017–5,379 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.0 GB	Q8_0	Comfortable
3,362 tok/s 2,017–5,379 · 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: University of Waterloo,RSVP.ai,Peking University
Organisation type: Academia,Industry,Academia
Country: Canada, China
Published: 30 April 2020
Authors: He Bai, Peng Shi, Jimmy Lin, Yuqing Xie, Luchen Tan, Kun Xiong, Wen Gao, Ming Li

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: 257M
Training data: tokens
Epochs: 18.64

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: 2.7 × 10¹⁹ FLOP

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.

Record confidence: Confident
Benchmark data: Segatron XL base, M=384

Sources

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

Reference: Segatron: Segment-Aware Transformer for Language Modeling and Understanding
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Segatron XL base, M=384

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 Segatron XL base, M=384

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

13,184 tok/s

Segatron XL base, M=384 is small enough at 257M 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 143 tokens per second.

At the other end, a B200 generates roughly 13,184 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

About this model

Segatron XL base, M=384 was published by University of Waterloo,RSVP.ai,Peking University, in Canada, in April 2020. The organisation is categorised as academia,Industry,Academia.

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.

How fast it runs, and why

The median result is around 370.2 tokens per second; 818 cards produce text faster than most people read it.

It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.

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.

How it was trained

Training it took roughly 2.7 × 10¹⁹ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for Segatron XL base, M=384

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 Segatron XL base, M=384 actually needs — around 1.0 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Segatron XL base, M=384.
03

Set a quality floor

Compression is what makes Segatron XL base, M=384 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

Compare tokens per second, not specifications

Sort by speed to see how cards rank for Segatron XL base, M=384. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 13,184 tok/s.
05

Read the fit column last

Tight means Segatron XL base, M=384 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 Segatron XL base, M=384.

Answers

Segatron XL base, M=384 — common questions

Is Segatron XL base, M=384 open source?

Its weights are published, so Segatron XL base, M=384 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 Segatron XL base, M=384 have?

Segatron XL base, M=384 has 257M 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 Segatron XL base, M=384?

Segatron XL base, M=384 was published by University of Waterloo,RSVP.ai,Peking University, based in Canada, categorised as academia,Industry,Academia.

When was Segatron XL base, M=384 released?

Segatron XL base, M=384 was published in April 2020. 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 Segatron XL base, M=384 used for?

Segatron XL base, M=384 works in Language, and is recorded as handling language modeling. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Segatron XL base, M=384?

The weights for Segatron XL base, M=384 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 Segatron XL base, M=384?

Around 2.7 × 10¹⁹ 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 Segatron XL base, M=384 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 Segatron XL base, M=384 assume it is fully resident.

Would two GPUs run Segatron XL base, M=384 faster?

Two cards buy memory rather than speed. That matters for Segatron XL base, M=384 only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for Segatron XL base, M=384?

Each card is shown running the least-compressed copy it can hold, and Segatron XL base, M=384 appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Segatron XL base, M=384 speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 7,910–21,094 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 Segatron XL base, M=384?

The smallest card in our catalogue that holds Segatron XL base, M=384 is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.0 GB, and produces roughly 143 tokens per second. 818 cards in total can run it.

How fast is Segatron XL base, M=384 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 13,184 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 Segatron XL base, M=384 clear that.

How much VRAM does Segatron XL base, M=384 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 Segatron XL base, M=384 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 2,455 tokens per second — a comfortable fit.

Can I run Segatron XL base, M=384 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 1,504 tokens per second — a comfortable fit.

Can I run Segatron XL base, M=384 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 1,862 tokens per second — a comfortable fit.

Can I run Segatron XL base, M=384 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 2,208 tokens per second — a comfortable fit.

Source

Original publication

Record last updated 28 November 2025

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