ManiGaussian

Open weights Tsinghua University,Nanyang Technological University,Carnegie Mellon University (CMU) March 2024

No estimate

No hardware requirements for this model

This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.

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
Tsinghua University,Nanyang Technological University,Carnegie Mellon University (CMU)
Organisation type
Academia,Academia,Academia
Country
China, Singapore, United States of America
Published
13 March 2024
Authors
Guanxing Lu, Shiyi Zhang, Ziwei Wang, Changliu Liu, Jiwen Lu, Yansong Tang

What it does

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

Domain
Robotics, Vision, Video
Task
Robotic manipulation

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.

Training data
tokens

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 GeForce RTX 4090
Chips used
2
Power draw
1.8 kW

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 https://github.com/GuanxingLu/ManiGaussian

How it is classified

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

Why it is tracked
SOTA improvement

1 Introduction: "We evaluate our ManiGaussian method on the RLBench dataset [27] with 10 tasks and 166 variants, where our method outperforms the state-of-the-art multi-task robotic manipulation methods by 13.1% in the average task success rate"

Record confidence
Confident
Citations
129

Sources

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

Reference
ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation
Last updated
25 May 2026

What the numbers mean

Where it came from

ManiGaussian was published by Tsinghua University,Nanyang Technological University,Carnegie Mellon University (CMU), in China, in March 2024. The organisation is categorised as academia,Academia,Academia.

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

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

How it was trained

The reason it appears in this catalogue at all is sOTA improvement.

Answers

ManiGaussian — common questions

01

Who created ManiGaussian?

ManiGaussian was published by Tsinghua University,Nanyang Technological University,Carnegie Mellon University (CMU), based in China, categorised as academia,Academia,Academia.

02

When was ManiGaussian released?

ManiGaussian was published in March 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.

03

What is ManiGaussian used for?

ManiGaussian works in Robotics, Vision, Video, and is recorded as handling robotic manipulation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

04

Where can I download ManiGaussian?

The weights for ManiGaussian are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

05

What GPU do I need to run ManiGaussian?

We cannot say. ManiGaussian has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.

06

Is ManiGaussian open source?

Its weights are published, so ManiGaussian 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.

07

How many parameters does ManiGaussian have?

No parameter count has been published for ManiGaussian, which is why no memory or speed figure appears on this page.

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.