GR00T N1 2B TPS calculator

Open weights NVIDIA 2.2B parameters March 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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 16.8 tok/s

Fastest card

B200

1,547 tok/s · 180 GB

Which GPUs can run GR00T N1 2B?

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
1,547 tok/s 928–2,475 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	3.0 GB	Q8_0	Comfortable
1,547 tok/s 928–2,475 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	3.0 GB	Q8_0	Comfortable
1,235 tok/s 741–1,977 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	3.0 GB	Q8_0	Comfortable
1,235 tok/s 741–1,977 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	3.0 GB	Q8_0	Comfortable
988 tok/s 593–1,581 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	3.0 GB	Q8_0	Comfortable
946 tok/s 567–1,513 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.0 GB	Q8_0	Comfortable
946 tok/s 567–1,513 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.0 GB	Q8_0	Comfortable
905 tok/s 543–1,448 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	3.0 GB	Q8_0	Comfortable
803 tok/s 482–1,285 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	3.0 GB	Q8_0	Comfortable
803 tok/s 482–1,285 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	3.0 GB	Q8_0	Comfortable
803 tok/s 482–1,285 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	3.0 GB	Q8_0	Comfortable
762 tok/s 457–1,219 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	3.0 GB	Q8_0	Comfortable
650 tok/s 390–1,040 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.0 GB	Q8_0	Comfortable
650 tok/s 390–1,040 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	3.0 GB	Q8_0	Comfortable
650 tok/s 390–1,040 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	3.0 GB	Q8_0	Comfortable
650 tok/s 390–1,040 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.0 GB	Q8_0	Comfortable
650 tok/s 390–1,040 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	3.0 GB	Q8_0	Comfortable
495 tok/s 297–792 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	3.0 GB	Q8_0	Comfortable
495 tok/s 297–792 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	3.0 GB	Q8_0	Comfortable
412 tok/s 247–660 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	3.0 GB	Q8_0	Comfortable
404 tok/s 242–646 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	3.0 GB	Q8_0	Comfortable
395 tok/s 237–631 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	3.0 GB	Q8_0	Comfortable
395 tok/s 237–631 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	3.0 GB	Q8_0	Comfortable
395 tok/s 237–631 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	3.0 GB	Q8_0	Comfortable
395 tok/s 237–631 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	3.0 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: NVIDIA
Organisation type: Industry
Country: United States of America
Published: 18 March 2025
Authors: Johan Bjorck, Fernando Castañeda, Nikita Cherniadev, Xingye Da, Runyu Ding, Linxi "Jim" Fan, Yu Fang, Dieter Fox, Fengyuan Hu, Spencer Huang, Joel Jang, Zhenyu Jiang, Jan Kautz, Kaushil Kundalia, Lawrence Lao, Zhiqi Li, Zongyu Lin, Kevin Lin, Guilin Liu, Edith Llontop, Loic Magne, Ajay Mandlekar, Avnish Narayan, Soroush Nasiriany, Scott Reed, You Liang Tan, Guanzhi Wang, Zu Wang, Jing Wang, Qi Wan…

What it does

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

Domain: Robotics, Vision, Language
Task: Robotic manipulation, Animal (human/non-human) imitation
Base model: Eagle 2
Numerical format: BF16

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: 2.2B
Training data: tokens
Batch size: 16,384

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: 7.1 × 10²² FLOP
How it was established: Hardware

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: 1,024
Wall-clock time: 49 hours
Power draw: 1.4 MW

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: Unreleased
Hugging Face: nvidia

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: 738

Sources

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

Reference: GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run GR00T N1 2B

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 GR00T N1 2B

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

Hardware requirements in practice

Minimum card

Tesla C1080

Memory needed

3.0 GB

Fastest

1,547 tok/s

GR00T N1 2B is small enough at 2.2B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The entry point is the Tesla C1080: 4 GB of memory, Q8_0 compression, roughly 16.8 tokens per second.

A B200 is the fastest we calculate for it: about 1,547 tokens per second, from 8,000 GB/s of memory bandwidth.

What this model is

GR00T N1 2B was published by NVIDIA, in United States of America, in March 2025. It comes out of industry.

It works in Robotics, Vision, Language, and is recorded as doing robotic manipulation, Animal (human/non-human) imitation.

It builds on Eagle 2, which is why it shares that model's general shape and size.

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. It is published under the nvidia organisation on Hugging Face.

What decides the speed

The median result is around 43.4 tokens per second; 787 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

Training it took roughly 7.1 × 10²² FLOP of computation, on NVIDIA H100 SXM5 80GB — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for GR00T N1 2B

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

01

Start from the memory column

Every card here has been checked against GR00T N1 2B — around 3.0 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason GR00T N1 2B stops fitting a card that seemed fine.
03

Decide how much compression you will accept

Compression is what makes GR00T N1 2B 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

Sort by speed

Ranking by tokens per second for GR00T N1 2B follows memory bandwidth, not core counts, which is why the B200 tops it at 1,547 tok/s.
05

Read the fit column last

A tight fit runs GR00T N1 2B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

See what else that card runs

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for GR00T N1 2B alone — a card is usually bought for more than one model.

Answers

GR00T N1 2B — common questions

How many parameters does GR00T N1 2B have?

GR00T N1 2B has 2.2B parameters. "Specifically, our publicly released GR00T-N1-2B model has 2.2B parameters in total, with 1.34B in the VLM." https://huggingface.co/nvidia/GR00T-N1-2B 2.19e9 parameters, bf16, 4.38 GB. 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 GR00T N1 2B?

GR00T N1 2B was published by NVIDIA, based in United States of America, categorised as industry.

When was GR00T N1 2B released?

GR00T N1 2B was published in March 2025.

What is GR00T N1 2B used for?

GR00T N1 2B works in Robotics, Vision, Language, and is recorded as handling robotic manipulation, Animal (human/non-human) imitation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download GR00T N1 2B?

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.

How much compute was used to train GR00T N1 2B?

Around 7.1 × 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.

Can I run GR00T N1 2B 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 GR00T N1 2B is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run GR00T N1 2B faster?

Two cards buy memory rather than speed. That matters for GR00T N1 2B only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for GR00T N1 2B?

Because capacity varies, so does how hard GR00T N1 2B has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these GR00T N1 2B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 928–2,475 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 GR00T N1 2B?

The smallest card in our catalogue that holds GR00T N1 2B is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 3.0 GB, and produces roughly 16.8 tokens per second. 818 cards in total can run it.

How fast is GR00T N1 2B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,547 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 787 of the cards that can run GR00T N1 2B clear that.

How much VRAM does GR00T N1 2B need?

About 3.0 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 GR00T N1 2B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 3.0 GB and generating roughly 288 tokens per second — a comfortable fit.

Can I run GR00T N1 2B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 3.0 GB and generating roughly 176 tokens per second — a comfortable fit.

Can I run GR00T N1 2B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 3.0 GB and generating roughly 219 tokens per second — a comfortable fit.

Can I run GR00T N1 2B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 3.0 GB and generating roughly 259 tokens per second — a comfortable fit.

Is GR00T N1 2B open source?

Its weights are published, so GR00T N1 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.

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