MiniMax-VL-01

Open weights MiniMax January 2025

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
MiniMax
Organisation type
Industry
Country
China
Published
14 January 2025
Authors
MiniMax, Aonian Li, Bangwei Gong, Bo Yang, Boji Shan, Chang Liu, Cheng Zhu, Chunhao Zhang, Congchao Guo, Da Chen, Dong Li, Enwei Jiao, Gengxin Li, Guojun Zhang, Haohai Sun, Houze Dong, Jiadai Zhu, Jiaqi Zhuang, Jiayuan Song, Jin Zhu, Jingtao Han, Jingyang Li, Junbin Xie, Junhao Xu, Junjie Yan, Kaishun Zhang, Kecheng Xiao, Kexi Kang, Le Han, Leyang Wang, Lianfei Yu, Liheng Feng, Lin Zheng, Linbo Ch…

What it does

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

Domain
Vision, Language, Multimodal
Task
Visual question answering, Language modeling/generation, Question answering
Base model
MiniMax-Text-01

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

"MiniMax-VL-01 undergoes additional training with 512 billion vision-language tokens"

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
2.1 × 10²⁴ FLOP

1.98288e+24 FLOP [base model compute] + 1.410048e+23 FLOP [addtional vision-language finetune compute] = 2.1238848e+24 FLOP

How it was established
Operation counting
Fine-tuning compute
1.4 × 10²³ FLOP

Assuming same amount of activated parameters (45.9 * 10^9) as for the base model: 6 FLOP / parameter / token * 45.9 * 10^9 activated parameters * 512 * 10^9 tokens = 1.410048e+23 FLOP

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 H800 SXM5

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
Unreleased

https://huggingface.co/MiniMaxAI/MiniMax-VL-01 "MiniMax may terminate this Agreement if you are in breach of any term or condition of this Agreement." code seems to be just inference code: https://github.com/MiniMax-AI/MiniMax-01

Hugging Face
MiniMaxAI

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
Likely

Sources

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

Reference
MiniMax-01: Scaling Foundation Models with Lightning Attention
Last updated
28 November 2025

What the numbers mean

Background

MiniMax-VL-01 was published by MiniMax, in China, in January 2025. It comes out of industry.

It works in Vision, Language, Multimodal, and is recorded as doing visual question answering, Language modeling/generation, Question answering.

Its starting point was MiniMax-Text-01 — most models at this scale are adapted from an existing base rather than built from nothing.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the MiniMaxAI organisation on Hugging Face.

How it was trained

Training it took roughly 2.1 × 10²⁴ FLOP of computation, on NVIDIA H800 SXM5 — a measure of what producing the model cost, not of how fast it answers.

Answers

MiniMax-VL-01 — common questions

01

What GPU do I need to run MiniMax-VL-01?

We cannot say. MiniMax-VL-01 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.

02

Is MiniMax-VL-01 open source?

Its weights are published, so MiniMax-VL-01 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.

03

How many parameters does MiniMax-VL-01 have?

No parameter count has been published for MiniMax-VL-01, which is why no memory or speed figure appears on this page.

04

Who created MiniMax-VL-01?

MiniMax-VL-01 was published by MiniMax, based in China, categorised as industry.

05

When was MiniMax-VL-01 released?

MiniMax-VL-01 was published in January 2025.

06

What is MiniMax-VL-01 used for?

MiniMax-VL-01 works in Vision, Language, Multimodal, and is recorded as handling visual question answering, Language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

07

Where can I download MiniMax-VL-01?

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

08

How much compute was used to train MiniMax-VL-01?

Around 2.1 × 10²⁴ FLOP, on NVIDIA H800 SXM5. 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.

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.