Pleias 1.0 1.2B TPS calculator

Open weights PleIAs 1.2B parameters December 2024

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 of 818 cards that can run it

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 30.7 tok/s

Fastest card

B200

2,824 tok/s · 180 GB

Which GPUs can run Pleias 1.0 1.2B?

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
2,824 tok/s

1,694–4,518 · low confidence

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 2.0 GB Q8_0 Comfortable
2,824 tok/s

1,694–4,518 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 2.0 GB Q8_0 Comfortable
2,255 tok/s

1,353–3,607 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 2.0 GB Q8_0 Comfortable
2,255 tok/s

1,353–3,607 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 2.0 GB Q8_0 Comfortable
1,803 tok/s

1,082–2,885 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 2.0 GB Q8_0 Comfortable
1,726 tok/s

1,036–2,761 · low confidence

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 2.0 GB Q8_0 Comfortable
1,726 tok/s

1,036–2,761 · low confidence

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 2.0 GB Q8_0 Comfortable
1,652 tok/s

991–2,643 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 2.0 GB Q8_0 Comfortable
1,466 tok/s

880–2,346 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 2.0 GB Q8_0 Comfortable
1,466 tok/s

880–2,346 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 2.0 GB Q8_0 Comfortable
1,466 tok/s

880–2,346 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 2.0 GB Q8_0 Comfortable
1,391 tok/s

834–2,225 · low confidence

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 2.0 GB Q8_0 Comfortable
1,186 tok/s

712–1,897 · low confidence

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 2.0 GB Q8_0 Comfortable
1,186 tok/s

712–1,897 · low confidence

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 2.0 GB Q8_0 Comfortable
1,186 tok/s

712–1,897 · low confidence

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 2.0 GB Q8_0 Comfortable
1,186 tok/s

712–1,897 · low confidence

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 2.0 GB Q8_0 Comfortable
1,186 tok/s

712–1,897 · low confidence

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 2.0 GB Q8_0 Comfortable
903 tok/s

542–1,445 · low confidence

Radeon Instinct MI250 AMD 128 GB 3,280 GB/s Nov 2021 2.0 GB Q8_0 Comfortable
903 tok/s

542–1,445 · low confidence

Radeon Instinct MI250X AMD 128 GB 3,280 GB/s Nov 2021 2.0 GB Q8_0 Comfortable
752 tok/s

451–1,204 · low confidence

Data Center GPU Max 1550 Intel 128 GB 3,280 GB/s Jan 2023 2.0 GB Q8_0 Comfortable
736 tok/s

442–1,178 · low confidence

Data Center GPU Max Subsystem Intel 128 GB 3,210 GB/s Jan 2023 2.0 GB Q8_0 Comfortable
720 tok/s

432–1,152 · low confidence

A100 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Nov 2020 2.0 GB Q8_0 Comfortable
720 tok/s

432–1,152 · low confidence

A100X NVIDIA 80 GB 2,040 GB/s Jun 2021 2.0 GB Q8_0 Comfortable
720 tok/s

432–1,152 · low confidence

A800 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Aug 2022 2.0 GB Q8_0 Comfortable
720 tok/s

432–1,152 · low confidence

H100 CNX NVIDIA 80 GB 2,040 GB/s Mar 2023 2.0 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
PleIAs
Organisation type
Industry
Country
France
Published
5 December 2024

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, Translation

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
1.2B

1.2B

Training data
tokens

"Training schedule includes 518,000 steps (batch size 1,024) on over three epochs (nearly 5 trillions tokens):"

Epochs
3

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
3 × 10²² FLOP

6 FLOP / parameter / token * 1.2 * 10^9 parameters * 5 * 10^12 tokens = 3.6e+22 FLOP 989400000000000 FLOP / GPU / sec [bf16 assumed] * 192 GPUs * 5 days * 24 hour / day * 3600 sec / hour * 0.3 [assumed utilization] = 2.4619438e+22 FLOP sqrt(3.6e+22*2.4619438e+22) = 2.9770787e+22

How it was established
Hardware,Operation counting

The training run

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

Training hardware
NVIDIA H100 SXM5 80GB
Chips used
192
Wall-clock time
120 hours

"Pleias-nano-1.2b-Preview was fully pretrained on TractoAI on ISEG GPU cluster by Nebius AI on 192 h100s for 5 days"

Power draw
264.3 kW
Cloud vendor
Nebius AI

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
Unreleased

Apache 2.0 https://huggingface.co/PleIAs/Pleias-350m-Preview

Hugging Face
PleIAs

How it is classified

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

Record confidence
Confident

Sources

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

Reference
Pleias-nano-1.2b-Preview
Last updated
28 November 2025

The extremes

What the numbers mean

What it takes to run this model

Minimum card

Tesla C1080

Memory needed

2.0 GB

Fastest

2,824 tok/s

Pleias 1.0 1.2B is small enough at 1.2B 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 30.7 tokens per second.

At the other end, a B200 generates roughly 2,824 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

About this model

Pleias 1.0 1.2B was published by PleIAs, in France, in December 2024. It comes out of industry.

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

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. It is published under the PleIAs organisation on Hugging Face.

How fast it runs, and why

The median result is around 79.3 tokens per second; 799 cards produce text faster than most people read it.

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.

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.

What went into building it

Producing it required around 3 × 10²² FLOP of arithmetic, on NVIDIA H100 SXM5 80GB, which is a statement about the training budget rather than about inference.

Step by step

How to choose a GPU for Pleias 1.0 1.2B

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

  1. 01

    Read the memory figure first

    Look at what Pleias 1.0 1.2B actually needs — around 2.0 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.

  2. 02

    Decide how long your conversations run

    The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Pleias 1.0 1.2B can slip off a card that handles short questions easily.

  3. 03

    Set a quality floor

    The quantisation column varies by card, because a bigger card holds a more accurate copy of Pleias 1.0 1.2B — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.

  4. 04

    Rank by throughput rather than spec sheet

    Ranking by tokens per second for Pleias 1.0 1.2B follows memory bandwidth, not core counts, which is why the B200 tops it at 2,824 tok/s.

  5. 05

    Look at the headroom, not just the fit

    A tight fit runs Pleias 1.0 1.2B 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

    Following a card through to its own page shows every other model it can hold, which is the question that follows once Pleias 1.0 1.2B is settled.

Answers

Pleias 1.0 1.2B — common questions

01

Can I run Pleias 1.0 1.2B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 2.0 GB and generating roughly 526 tokens per second — a comfortable fit.

02

Can I run Pleias 1.0 1.2B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 2.0 GB and generating roughly 322 tokens per second — a comfortable fit.

03

Can I run Pleias 1.0 1.2B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 2.0 GB and generating roughly 399 tokens per second — a comfortable fit.

04

Can I run Pleias 1.0 1.2B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 2.0 GB and generating roughly 473 tokens per second — a comfortable fit.

05

Is Pleias 1.0 1.2B open source?

Its weights are published, so Pleias 1.0 1.2B 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.

06

How many parameters does Pleias 1.0 1.2B have?

Pleias 1.0 1.2B has 1.2B parameters. 1.2B. 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.

07

Who created Pleias 1.0 1.2B?

Pleias 1.0 1.2B was published by PleIAs, based in France, categorised as industry.

08

When was Pleias 1.0 1.2B released?

Pleias 1.0 1.2B was published in December 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

09

What is Pleias 1.0 1.2B used for?

Pleias 1.0 1.2B works in Language, and is recorded as handling language modeling/generation, Question answering, Translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

10

Where can I download Pleias 1.0 1.2B?

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

11

How much compute was used to train Pleias 1.0 1.2B?

Around 3 × 10²² FLOP, on NVIDIA H100 SXM5 80GB. 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.

12

Can I run Pleias 1.0 1.2B 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 Pleias 1.0 1.2B assume it is fully resident.

13

Would two GPUs run Pleias 1.0 1.2B faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run Pleias 1.0 1.2B alone, the case for pairing is weak.

14

Why does the quantisation differ between cards for Pleias 1.0 1.2B?

Because capacity varies, so does how hard Pleias 1.0 1.2B has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

15

How accurate are these Pleias 1.0 1.2B 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 1,694–4,518 tok/s on the B200 rather than a single number.

16

What GPU do I need to run Pleias 1.0 1.2B?

The smallest card in our catalogue that holds Pleias 1.0 1.2B is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 2.0 GB, and produces roughly 30.7 tokens per second. 818 cards in total can run it.

17

How fast is Pleias 1.0 1.2B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 2,824 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 799 of the cards that can run Pleias 1.0 1.2B clear that.

18

How much VRAM does Pleias 1.0 1.2B need?

About 2.0 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.

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.