Cosmos-Predict2-14B-Video2World TPS calculator

Open weights NVIDIA 14B parameters June 2025

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

306 cards that can run it

818 cards we hold specifications for

Smallest card that fits

P102-101

10 GB · IQ4_XS · 20.2 tok/s

Fastest card

B200

242 tok/s · 180 GB

Which GPUs can run Cosmos-Predict2-14B-Video2World?

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.

306 cards match

Calculating
Needs Quantisation Fit
242 tok/s

145–387 · low confidence

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 15.7 GB Q8_0 Comfortable
242 tok/s

145–387 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 15.7 GB Q8_0 Comfortable
193 tok/s

116–309 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 15.7 GB Q8_0 Comfortable
193 tok/s

116–309 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 15.7 GB Q8_0 Comfortable
155 tok/s

93–247 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 15.7 GB Q8_0 Comfortable
148 tok/s

89–237 · low confidence

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 15.7 GB Q8_0 Comfortable
148 tok/s

89–237 · low confidence

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 15.7 GB Q8_0 Comfortable
142 tok/s

85–227 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 15.7 GB Q8_0 Comfortable
126 tok/s

75–201 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 15.7 GB Q8_0 Comfortable
126 tok/s

75–201 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 15.7 GB Q8_0 Comfortable
126 tok/s

75–201 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 15.7 GB Q8_0 Comfortable
119 tok/s

72–191 · low confidence

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 15.7 GB Q8_0 Comfortable
116 tok/s

70–185 · low confidence

CMP 170HX 10 GB NVIDIA 10 GB 1,560 GB/s Sep 2021 8.4 GB IQ4_XS Tight
102 tok/s

61–163 · low confidence

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 15.7 GB Q8_0 Comfortable
102 tok/s

61–163 · low confidence

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 15.7 GB Q8_0 Comfortable
102 tok/s

61–163 · low confidence

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 15.7 GB Q8_0 Comfortable
102 tok/s

61–163 · low confidence

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 15.7 GB Q8_0 Comfortable
102 tok/s

61–163 · low confidence

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 15.7 GB Q8_0 Comfortable
77.4 tok/s

46–124 · low confidence

Radeon Instinct MI250 AMD 128 GB 3,280 GB/s Nov 2021 15.7 GB Q8_0 Comfortable
77.4 tok/s

46–124 · low confidence

Radeon Instinct MI250X AMD 128 GB 3,280 GB/s Nov 2021 15.7 GB Q8_0 Comfortable
64.5 tok/s

39–103 · low confidence

Data Center GPU Max 1550 Intel 128 GB 3,280 GB/s Jan 2023 15.7 GB Q8_0 Comfortable
63.1 tok/s

38–101 · low confidence

Data Center GPU Max Subsystem Intel 128 GB 3,210 GB/s Jan 2023 15.7 GB Q8_0 Comfortable
61.7 tok/s

37–99 · low confidence

A100 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Nov 2020 15.7 GB Q8_0 Comfortable
61.7 tok/s

37–99 · low confidence

A100X NVIDIA 80 GB 2,040 GB/s Jun 2021 15.7 GB Q8_0 Comfortable
61.7 tok/s

37–99 · low confidence

A800 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Aug 2022 15.7 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
NVIDIA
Organisation type
Industry
Country
United States of America
Published
11 June 2025

What it does

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

Domain
Video, Vision, Robotics
Task
Robotic manipulation, System control, Video 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
14B
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 (restricted use)
Training code
Open source

NVIDIA license (termination clause + attribution requirements) https://huggingface.co/nvidia/Cosmos-Predict2-14B-Video2World Apache 2.0 for code https://github.com/nvidia-cosmos/cosmos-predict2/tree/main

Hugging Face
nvidia

How it is classified

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

Likely above 10²³ FLOP
Yes
Record confidence
Confident

Sources

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

Reference
NVIDIA Releases New AI Models and Developer Tools to Advance Autonomous Vehicle Ecosystem
Last updated
28 November 2025

The extremes

What the numbers mean

What it takes to run this model

Minimum card

P102-101

Memory needed

8.4 GB

Fastest

242 tok/s

Cosmos-Predict2-14B-Video2World is small enough at 14B parameters that hardware is rarely the obstacle — 306 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the P102-101 with 10 GB, running it at IQ4_XS and producing around 20.2 tokens per second.

Top of the range is the B200, at roughly 242 tokens per second thanks to 8,000 GB/s of bandwidth.

Where it came from

Cosmos-Predict2-14B-Video2World was published by NVIDIA, in United States of America, in June 2025. industry is the category the publisher falls under.

It works in Video, Vision, Robotics, and is recorded as doing robotic manipulation, System control, Video generation.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the nvidia organisation on Hugging Face.

Understanding the speeds

Half the cards that hold it manage more than 20.4 tokens per second, and 268 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.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

Step by step

How to choose a GPU for Cosmos-Predict2-14B-Video2World

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

    The table lists every card that can hold Cosmos-Predict2-14B-Video2World — around 8.4 GB at IQ4_XS. That figure, not the card's headline performance, is what decides whether it runs.

  2. 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 Cosmos-Predict2-14B-Video2World.

  3. 03

    Set a quality floor

    The quantisation column varies by card, because a bigger card holds a more accurate copy of Cosmos-Predict2-14B-Video2World — IQ4_XS on the smallest card that fits. Set a floor to hold the comparison at one level.

  4. 04

    Sort by speed

    Sort by speed to see how cards rank for Cosmos-Predict2-14B-Video2World. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 242 tok/s.

  5. 05

    Read the fit column last

    The fit column separates cards that just manage Cosmos-Predict2-14B-Video2World from those with room to spare. Buy for the second if the context might grow.

  6. 06

    Check the card from the other side

    Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Cosmos-Predict2-14B-Video2World.

Answers

Cosmos-Predict2-14B-Video2World — common questions

01

Why does the quantisation differ between cards for Cosmos-Predict2-14B-Video2World?

A larger card holds a more accurate copy. Across the cards that run Cosmos-Predict2-14B-Video2World, 5 compression levels are used; the floor control above pins it to one.

02

How accurate are these Cosmos-Predict2-14B-Video2World 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 145–387 tok/s on the B200 rather than a single number.

03

What GPU do I need to run Cosmos-Predict2-14B-Video2World?

The smallest card in our catalogue that holds Cosmos-Predict2-14B-Video2World is the P102-101, with 10 GB of memory. It runs the model at IQ4_XS using about 8.4 GB, and produces roughly 20.2 tokens per second. 306 cards in total can run it.

04

How fast is Cosmos-Predict2-14B-Video2World on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 242 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 268 of the cards that can run Cosmos-Predict2-14B-Video2World clear that.

05

How much VRAM does Cosmos-Predict2-14B-Video2World need?

About 8.4 GB at IQ4_XS 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.

06

Can I run Cosmos-Predict2-14B-Video2World on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q5_K_M, using about 10.8 GB and generating roughly 49.3 tokens per second — a tight fit.

07

Can I run Cosmos-Predict2-14B-Video2World on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 12.4 GB and generating roughly 49.7 tokens per second — a tight fit.

08

Can I run Cosmos-Predict2-14B-Video2World on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 15.7 GB and generating roughly 40.5 tokens per second — a comfortable fit.

09

Is Cosmos-Predict2-14B-Video2World open source?

Its weights are published, so Cosmos-Predict2-14B-Video2World 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.

10

How many parameters does Cosmos-Predict2-14B-Video2World have?

Cosmos-Predict2-14B-Video2World has 14B 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.

11

Who created Cosmos-Predict2-14B-Video2World?

Cosmos-Predict2-14B-Video2World was published by NVIDIA, based in United States of America, categorised as industry.

12

When was Cosmos-Predict2-14B-Video2World released?

Cosmos-Predict2-14B-Video2World was published in June 2025.

13

What is Cosmos-Predict2-14B-Video2World used for?

Cosmos-Predict2-14B-Video2World works in Video, Vision, Robotics, and is recorded as handling robotic manipulation, System control, Video generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

14

Where can I download Cosmos-Predict2-14B-Video2World?

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

15

Can I run Cosmos-Predict2-14B-Video2World 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 Cosmos-Predict2-14B-Video2World is rarely worth using — the nearest miss we calculate is short by 2.0 GB. Every figure here assumes the whole model is on the card.

16

Would two GPUs run Cosmos-Predict2-14B-Video2World faster?

Two cards buy memory rather than speed. That matters for Cosmos-Predict2-14B-Video2World only if one card cannot hold it — 306 can, so a second adds little.

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.