NVLM-D 72B TPS calculator

Open weights NVIDIA 72B parameters October 2024

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

61 cards that can run it

818 cards we hold specifications for

Smallest card that fits

A100 PCIe 40 GB

40 GB · Q3_K_M · 24.8 tok/s

Fastest card

B200

47.1 tok/s · 180 GB

Which GPUs can run NVLM-D 72B?

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

61 cards match

Calculating

					Needs	Quantisation	Fit
47.1 tok/s 28–75 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	77.8 GB	Q8_0	Comfortable
47.1 tok/s 28–75 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	77.8 GB	Q8_0	Comfortable
37.6 tok/s 23–60 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	77.8 GB	Q8_0	Comfortable
37.6 tok/s 23–60 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	77.8 GB	Q8_0	Comfortable
30.1 tok/s 18–48 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	77.8 GB	Q8_0	Comfortable
28.8 tok/s 17–46 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	77.8 GB	Q8_0	Comfortable
28.8 tok/s 17–46 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	77.8 GB	Q8_0	Comfortable
28.7 tok/s 17–46 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	61.0 GB	Q6_K	Tight
28.7 tok/s 17–46 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	61.0 GB	Q6_K	Tight
27.5 tok/s 17–44 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	77.8 GB	Q8_0	Comfortable
27.0 tok/s 16–43 · low confidence	GRID A100B NVIDIA	48 GB	1,870 GB/s	May 2020	40.1 GB	IQ4_XS	Tight
24.8 tok/s 15–40 · low confidence	A100 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Jun 2020	35.9 GB	Q3_K_M	Tight
24.8 tok/s 15–40 · low confidence	A100 SXM4 40 GB NVIDIA	40 GB	1,560 GB/s	May 2020	35.9 GB	Q3_K_M	Tight
24.8 tok/s 15–40 · low confidence	A800 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Nov 2022	35.9 GB	Q3_K_M	Tight
24.4 tok/s 15–39 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	77.8 GB	Q8_0	Comfortable
24.4 tok/s 15–39 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	77.8 GB	Q8_0	Comfortable
24.4 tok/s 15–39 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	77.8 GB	Q8_0	Comfortable
23.2 tok/s 14–37 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	77.8 GB	Q8_0	Tight
21.2 tok/s 13–34 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	52.6 GB	Q5_K_M	Tight
19.8 tok/s 12–32 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	77.8 GB	Q8_0	Tight
19.8 tok/s 12–32 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	77.8 GB	Q8_0	Tight
19.8 tok/s 12–32 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	77.8 GB	Q8_0	Tight
19.4 tok/s 12–31 · low confidence	RTX PRO 5000 Blackwell NVIDIA	48 GB	1,340 GB/s	Mar 2025	40.1 GB	IQ4_XS	Tight
17.4 tok/s 10–28 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	61.0 GB	Q6_K	Tight
17.4 tok/s 10–28 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	61.0 GB	Q6_K	Tight

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: 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
Training data: 57,016,320,000 tokens
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
How it was established: Operation counting
Fine-tuning compute: 2.5 × 10²² 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 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: Open — downloadable
Model access: Open weights (non-commercial)
Training code: Open source
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
Why it is tracked: SOTA improvement
Record confidence: Confident

Sources

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

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

The extremes

The ten fastest GPUs that run NVLM-D 72B

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 NVLM-D 72B

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

What you need to run it

Minimum card

A100 PCIe 40 GB

Memory needed

35.9 GB

Fastest

47.1 tok/s

NVLM-D 72B reaches a parameter count of 72B. That puts it above consumer hardware, into the range where a card is bought for this purpose rather than repurposed for it. The number of cards we track that can hold it: 61.

The least hardware that works is A100 PCIe 40 GB, with a memory capacity of 40 GB, running it at a compression of Q3_K_M and producing around 24.8 tokens per second.

The fastest we calculate for it is B200, generating roughly 47.1 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Where it came from

NVLM-D 72B was published by NVIDIA, in the country recorded as United States of America, during October 2024. The publishing organisation is categorised as industry.

It works in the domain of Vision, Language, and is recorded as performing the task of language modeling/generation, Vision-language generation, Question answering, Code generation, Translation, Quantitative reasoning.

Its starting point was an existing base model, Qwen2-72B,InternViT-6B. That is the usual way a specialised model is produced.

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. On Hugging Face it is published under the organisation nvidia.

Understanding the speeds

Across every card that can run it, the middle of the range sits at 16.6 tokens per second. Producing text faster than most people read it: 51 of them.

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.

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.

What went into building it

Training it took a computation budget of roughly 3 × 10²⁴ FLOP, on hardware recorded as NVIDIA H100 SXM5 80GB. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 57,016,320,000 tokens of text.

Its inclusion criterion: sOTA improvement.

Step by step

How to choose a GPU for NVLM-D 72B

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

01

Check what it needs before anything else

Every card here has been checked against NVLM-D 72B, needing around 35.9 GB at a compression of Q3_K_M. That figure, not the headline performance of a card, is what decides whether it runs.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect, because at long context a card that handles short questions easily can be dropped by NVLM-D 72B.
03

Set a quality floor

Each card runs the least-compressed copy it can hold, reaching a compression of Q3_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second follows memory bandwidth rather than core counts, for NVLM-D 72B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 47.1 tok/s.
05

Look at the headroom, not just the fit

Tight means it loads and works with no room to raise the context later, in the case of NVLM-D 72B. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
06

Check the card from the other side

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond NVLM-D 72B.

Answers

NVLM-D 72B — common questions

NVLM-D 72B— when was it released?

It 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.

NVLM-D 72B— what is it used for?

It works in the domain of Vision, Language, and is recorded as handling the task of language modeling/generation, Vision-language generation, Question answering, Code generation, Translation, Quantitative reasoning. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

NVLM-D 72B— where can I download it?

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

NVLM-D 72B— how much compute was used to train it?

Training consumed around 3 × 10²⁴ FLOP, on hardware recorded as 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.

NVLM-D 72B— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 15.5 GB. Every figure here assumes the whole model is resident on the card.

NVLM-D 72B— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 61. So a second card is rarely the answer here.

NVLM-D 72B— why does the quantisation differ between cards?

A larger card holds a more accurate copy. The number of compression levels used across the cards that run it: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

NVLM-D 72B— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 28–75 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

NVLM-D 72B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is A100 PCIe 40 GB, with a memory capacity of 40 GB. It runs the model at a compression of Q3_K_M using about 35.9 GB, and produces roughly 24.8 tokens per second. The number of cards able to run it in total: 61.

NVLM-D 72B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 47.1 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 51.

NVLM-D 72B— how much VRAM does it need?

It needs about 35.9 GB at a compression of Q3_K_M, 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.

NVLM-D 72B— is it open source?

Its weights are published, so it 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.

NVLM-D 72B— how many parameters does it have?

It has a parameter count of 72B. 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.

NVLM-D 72B— who created it?

It was published by NVIDIA, based in United States of America, an organisation categorised as industry.

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.

All AI models