InternVL TPS calculator

Open weights Shanghai AI Lab,Nanjing University,The University of Hong Kong,Tsinghua University,SenseTime,University of Science and Technology of China (USTC) 14B parameters January 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

306 cards that can run it

818 cards we hold specifications for

Smallest card that fits

P102-101

10 GB · IQ4_XS · 20.2 tok/s

Fastest card

B200

242 tok/s · 180 GB

Which GPUs can run InternVL?

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

306 cards match

Calculating

					Needs	Quantisation	Fit
242 tok/s 145–387 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	15.7 GB	Q8_0	Comfortable
242 tok/s 145–387 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	15.7 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	15.7 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	15.7 GB	Q8_0	Comfortable
155 tok/s 93–247 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	15.7 GB	Q8_0	Comfortable
148 tok/s 89–237 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	15.7 GB	Q8_0	Comfortable
148 tok/s 89–237 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	15.7 GB	Q8_0	Comfortable
142 tok/s 85–227 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	15.7 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	15.7 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	15.7 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	15.7 GB	Q8_0	Comfortable
119 tok/s 72–191 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	15.7 GB	Q8_0	Comfortable
116 tok/s 70–185 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.4 GB	IQ4_XS	Tight
102 tok/s 61–163 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	15.7 GB	Q8_0	Comfortable
102 tok/s 61–163 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	15.7 GB	Q8_0	Comfortable
102 tok/s 61–163 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	15.7 GB	Q8_0	Comfortable
102 tok/s 61–163 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	15.7 GB	Q8_0	Comfortable
102 tok/s 61–163 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	15.7 GB	Q8_0	Comfortable
77.4 tok/s 46–124 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	15.7 GB	Q8_0	Comfortable
77.4 tok/s 46–124 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	15.7 GB	Q8_0	Comfortable
64.5 tok/s 39–103 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	15.7 GB	Q8_0	Comfortable
63.1 tok/s 38–101 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	15.7 GB	Q8_0	Comfortable
61.7 tok/s 37–99 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	15.7 GB	Q8_0	Comfortable
61.7 tok/s 37–99 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	15.7 GB	Q8_0	Comfortable
61.7 tok/s 37–99 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	15.7 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: Shanghai AI Lab,Nanjing University,The University of Hong Kong,Tsinghua University,SenseTime,University of Science and Technology of China (USTC)
Organisation type: Academia,Academia,Academia,Academia,Industry,Academia
Country: China, Hong Kong
Published: 15 January 2024
Authors: Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, Jifeng Dai

What it does

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

Domain: Vision, Language
Task: Visual question answering, Image classification, Image captioning
Base model: InternViT-6B,LLaMA-7B
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: 14B
Training data: tokens
Batch size: 164,000

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: 1.7 × 10²³ FLOP
How it was established: Operation counting

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 A100 SXM4 80 GB
Chips used: 640
Wall-clock time: 800 hours (33.3 days)
Power draw: 507.1 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: Unreleased
Hugging Face: OpenGVLab

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: InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run InternVL

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 InternVL

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

The hardware side

Minimum card

P102-101

Memory needed

8.4 GB

Fastest

242 tok/s

InternVL reaches a parameter count of 14B. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 306.

At the low end it is handled by P102-101, with a memory capacity of 10 GB, running it at a compression of IQ4_XS and producing around 20.2 tokens per second.

At the other end sits B200, generating roughly 242 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

InternVL was published by Shanghai AI Lab,Nanjing University,The University of Hong Kong,Tsinghua University,SenseTime,University of Science and Technology of China (USTC), in the country recorded as China, during January 2024. The publishing organisation is categorised as academia,Academia,Academia,Academia,Industry,Academia.

It works in the domain of Vision, Language, and is recorded as performing the task of visual question answering, Image classification, Image captioning.

It builds on InternViT-6B,LLaMA-7B. That is why it shares the base 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. On Hugging Face it is published under the organisation OpenGVLab.

Reading the throughput figures

The median result is around 20.4 tokens per second. Exceeding reading speed outright: 268 of them.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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.

Training and provenance

Training it took a computation budget of roughly 1.7 × 10²³ FLOP, on hardware recorded as NVIDIA A100 SXM4 80 GB. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Step by step

How to choose a GPU for InternVL

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 InternVL, needing around 8.4 GB at a compression of IQ4_XS. No amount of processing power compensates for a card that cannot hold it.
02

Match the context to your actual use

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for InternVL.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of IQ4_XS 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

Sort by speed

Ranking by tokens per second follows memory bandwidth rather than core counts, for InternVL. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 242 tok/s.
05

Check the fit verdict before buying

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of InternVL. 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

Open the card you have settled on

Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for InternVL.

Answers

InternVL — common questions

InternVL— can I run it 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 model is rarely worth using. The nearest miss we calculate falls short by 2.0 GB. Every figure here assumes the whole model is resident on the card.

InternVL— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 306. So a second card is rarely the answer here.

InternVL— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

InternVL— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 145–387 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

InternVL— what GPU do I need to run it?

The smallest card in our catalogue that holds it is P102-101, with a memory capacity of 10 GB. It runs the model at a compression of IQ4_XS using about 8.4 GB, and produces roughly 20.2 tokens per second. The number of cards able to run it in total: 306.

InternVL— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 242 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: 268.

InternVL— how much VRAM does it need?

It needs about 8.4 GB at a compression of IQ4_XS, 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.

InternVL— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of Q5_K_M, using about 10.8 GB and generating roughly 49.3 tokens per second. The fit is tight.

InternVL— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q6_K, using about 12.4 GB and generating roughly 49.7 tokens per second. The fit is tight.

InternVL— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q8_0, using about 15.7 GB and generating roughly 40.5 tokens per second. The fit is comfortable.

InternVL— 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.

InternVL— how many parameters does it have?

It has a parameter count of 14B. 14B. 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.

InternVL— who created it?

It was published by Shanghai AI Lab,Nanjing University,The University of Hong Kong,Tsinghua University,SenseTime,University of Science and Technology of China (USTC), based in China, an organisation categorised as academia,Academia,Academia,Academia,Industry,Academia.

InternVL— when was it released?

It was published in January 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.

InternVL— what is it used for?

It works in the domain of Vision, Language, and is recorded as handling the task of visual question answering, Image classification, Image captioning. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

InternVL— where can I download it?

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

InternVL— how much compute was used to train it?

Training consumed around 1.7 × 10²³ FLOP, on hardware recorded as NVIDIA A100 SXM4 80 GB. 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.

All AI models