NVLM-X 72B

Closed weights NVIDIA 72B parameters October 2024

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

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
22 October 2024
Authors
Wenliang Dai, Nayeon Lee, Boxin Wang, Zhuolin Yang, Zihan Liu, Jon Barker, Tuomas Rintamaki, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping

What it does

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

Domain
Vision, Language
Task
Language modeling/generation, Vision-language generation, Question answering, Code generation, Translation, Quantitative reasoning
Base model
Qwen2-72B,InternViT-6B
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
72B

72B

Training data
45,875,200,000 tokens

Pre-training Global batch size 2,048 Sequence length in the LLM decoder 512 Downsampling of visual tokens 1024->256 # of visual token per tile 256 # of tiles 1 # of training steps 20K 2048 * (512 + 256 * 1) * 20000 = 31,457,280,000 SFT: Global batch size 256 Sequence length in the LLM decoder 1,024 # of visual token per tile 256 # of tiles 6+1 # of training steps 20K 256 * (1,024 + 256*7) * 20000 = 14417920000 31,457,280,000 +14417920000 = 45875200000

Epochs
1

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 × 10²⁴ FLOP

3.02e24 FLOP (Qwen2-72B compute) + 19818086000000000000000 = 3.0398181e+24

How it was established
Operation counting
Fine-tuning compute
2 × 10²² FLOP

6*72B*45875200000 = 1.9818086e+22

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
128
Power draw
176.4 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
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

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
Why it is tracked
Training cost
Record confidence
Likely

Sources

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

Reference
NVLM: Open Frontier-Class Multimodal LLMs
Last updated
28 November 2025

What the numbers mean

Background

NVLM-X 72B was published by NVIDIA, in United States of America, in October 2024. industry is the category the publisher falls under.

It works in Vision, Language, and is recorded as doing language modeling/generation, Vision-language generation, Question answering, Code generation, Translation, Quantitative reasoning.

Its starting point was Qwen2-72B,InternViT-6B — most models at this scale are adapted from an existing base rather than built from nothing.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

Training it took roughly 3 × 10²⁴ FLOP of computation, on NVIDIA H100 SXM5 80GB — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 45,875,200,000 tokens.

It is tracked in the underlying dataset for one reason in particular: training cost.

Answers

NVLM-X 72B — common questions

01

Is NVLM-X 72B open source?

No. NVLM-X 72B has not had its weights published, so it exists only as a service controlled by its owner.

02

How many parameters does NVLM-X 72B have?

NVLM-X 72B has 72B parameters. 72B. 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.

03

Who created NVLM-X 72B?

NVLM-X 72B was published by NVIDIA, based in United States of America, categorised as industry.

04

When was NVLM-X 72B released?

NVLM-X 72B was published in October 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.

05

What is NVLM-X 72B used for?

NVLM-X 72B works in Vision, Language, and is recorded as handling language modeling/generation, Vision-language generation, Question answering, Code generation, Translation, Quantitative reasoning. 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.

06

How much compute was used to train NVLM-X 72B?

Around 3 × 10²⁴ 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.

07

What GPU do I need to run NVLM-X 72B?

None. NVLM-X 72B is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

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.