InternVL2-Llama3-76B TPS calculator
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
Smallest card that fits
Quadro RTX 8000
48 GB · IQ4_XS · 9.2 tok/s
Fastest card
B200
44.6 tok/s · 180 GB
Which GPUs can run InternVL2-Llama3-76B?
Set the inputs, read the answer
A longer conversation needs more memory, which can push this model off smaller cards.
Hides cards that would only fit the model by compressing it below this point.
58 cards match
Calculating| Needs | Quantisation | Fit | |||||
|---|---|---|---|---|---|---|---|
|
44.6
tok/s
27–71 · low confidence |
B200 NVIDIA | 180 GB | 8,000 GB/s | Jan 2024 | 82.1 GB | Q8_0 | Comfortable |
|
44.6
tok/s
27–71 · low confidence |
B300 NVIDIA | 288 GB | 8,000 GB/s | Sep 2025 | 82.1 GB | Q8_0 | Comfortable |
|
35.6
tok/s
21–57 · low confidence |
Radeon Instinct MI350X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 82.1 GB | Q8_0 | Comfortable |
|
35.6
tok/s
21–57 · low confidence |
Radeon Instinct MI355X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 82.1 GB | Q8_0 | Comfortable |
|
28.5
tok/s
17–46 · low confidence |
Radeon Instinct MI300 AMD | 128 GB | 6,550 GB/s | Jan 2023 | 82.1 GB | Q8_0 | Comfortable |
|
27.3
tok/s
16–44 · low confidence |
H200 NVL NVIDIA | 141 GB | 4,890 GB/s | Nov 2024 | 82.1 GB | Q8_0 | Comfortable |
|
27.3
tok/s
16–44 · low confidence |
H200 SXM 141 GB NVIDIA | 141 GB | 4,890 GB/s | Nov 2024 | 82.1 GB | Q8_0 | Comfortable |
|
27.2
tok/s
16–44 · low confidence |
H100 SXM5 80 GB NVIDIA | 80 GB | 3,360 GB/s | Oct 2022 | 64.4 GB | Q6_K | Tight |
|
27.2
tok/s
16–44 · low confidence |
H800 SXM5 NVIDIA | 80 GB | 3,360 GB/s | Mar 2023 | 64.4 GB | Q6_K | Tight |
|
26.1
tok/s
16–42 · low confidence |
Radeon Instinct MI325X AMD | 256 GB | 6,000 GB/s | Oct 2024 | 82.1 GB | Q8_0 | Comfortable |
|
25.6
tok/s
15–41 · low confidence |
GRID A100B NVIDIA | 48 GB | 1,870 GB/s | May 2020 | 42.3 GB | IQ4_XS | Tight |
|
23.2
tok/s
14–37 · low confidence |
Radeon Instinct MI300A AMD | 128 GB | 5,325 GB/s | Dec 2023 | 82.1 GB | Q8_0 | Comfortable |
|
23.2
tok/s
14–37 · low confidence |
Radeon Instinct MI300X AMD | 192 GB | 5,325 GB/s | Dec 2023 | 82.1 GB | Q8_0 | Comfortable |
|
23.2
tok/s
14–37 · low confidence |
Radeon Instinct MI308X AMD | 192 GB | 5,325 GB/s | Dec 2023 | 82.1 GB | Q8_0 | Comfortable |
|
22.0
tok/s
13–35 · low confidence |
H100 NVL 94 GB NVIDIA | 94 GB | 3,940 GB/s | Mar 2023 | 82.1 GB | Q8_0 | Tight |
|
20.1
tok/s
12–32 · low confidence |
H100 SXM5 64 GB NVIDIA | 64 GB | 2,020 GB/s | Mar 2023 | 55.5 GB | Q5_K_M | Tight |
|
18.7
tok/s
11–30 · low confidence |
H100 PCIe 96 GB NVIDIA | 96 GB | 3,360 GB/s | Mar 2023 | 82.1 GB | Q8_0 | Tight |
|
18.7
tok/s
11–30 · low confidence |
H100 SXM5 94 GB NVIDIA | 94 GB | 3,360 GB/s | Mar 2023 | 82.1 GB | Q8_0 | Tight |
|
18.7
tok/s
11–30 · low confidence |
H100 SXM5 96 GB NVIDIA | 96 GB | 3,360 GB/s | Mar 2023 | 82.1 GB | Q8_0 | Tight |
|
18.3
tok/s
11–29 · low confidence |
RTX PRO 5000 Blackwell NVIDIA | 48 GB | 1,340 GB/s | Mar 2025 | 42.3 GB | IQ4_XS | Tight |
|
16.5
tok/s
10–26 · low confidence |
A100 SXM4 80 GB NVIDIA | 80 GB | 2,040 GB/s | Nov 2020 | 64.4 GB | Q6_K | Tight |
|
16.5
tok/s
10–26 · low confidence |
A100X NVIDIA | 80 GB | 2,040 GB/s | Jun 2021 | 64.4 GB | Q6_K | Tight |
|
16.5
tok/s
10–26 · low confidence |
A800 SXM4 80 GB NVIDIA | 80 GB | 2,040 GB/s | Aug 2022 | 64.4 GB | Q6_K | Tight |
|
16.5
tok/s
10–26 · low confidence |
H100 CNX NVIDIA | 80 GB | 2,040 GB/s | Mar 2023 | 64.4 GB | Q6_K | Tight |
|
16.5
tok/s
10–26 · low confidence |
H100 PCIe 80 GB NVIDIA | 80 GB | 2,040 GB/s | Oct 2022 | 64.4 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
- Shanghai AI Lab
- Organisation type
- Academia
- Country
- China
- Published
- 15 July 2024
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Multimodal, Language, Vision, Video
- Task
- Visual question answering, Language modeling/generation, Question answering, Video description
- Base model
- Hermes 2 Theta Llama-3 70B,InternViT-6B
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
- 76B
- Training data
- tokens
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
- Open source
- Hugging Face
- OpenGVLab
llama3 license https://huggingface.co/OpenGVLab/InternVL2-Llama3-76B "This project is released under the MIT License. This project uses the pre-trained Hermes-2-Theta-Llama-3-70B as a component, which is licensed under the Llama 3 Community License." MIT license https://github.com/OpenGVLab/InternVL "Release training / evaluation code for InternVL2 series" is checked off
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- OpenGVLab/InternVL2-Llama3-76B
- Last updated
- 28 November 2025
The extremes
The ten fastest GPUs for InternVL2-Llama3-76B
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.
- 01 B300 288 GB · 8,000 GB/s · Q8_0 44.6 tok/s
- 02 B200 180 GB · 8,000 GB/s · Q8_0 44.6 tok/s
- 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 35.6 tok/s
- 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 35.6 tok/s
- 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 28.5 tok/s
- 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 27.3 tok/s
- 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 27.3 tok/s
- 08 H800 SXM5 80 GB · 3,360 GB/s · Q6_K 27.2 tok/s
- 09 H100 SXM5 80 GB 80 GB · 3,360 GB/s · Q6_K 27.2 tok/s
- 10 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 26.1 tok/s
The smallest GPUs that still run InternVL2-Llama3-76B
The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.
- 01 Radeon PRO W7900D 48 GB · needs 42.3 GB · IQ4_XS · tight 9.2 tok/s
- 02 RTX PRO 5000 Blackwell 48 GB · needs 42.3 GB · IQ4_XS · tight 18.3 tok/s
- 03 RTX 5880 Ada Generation 48 GB · needs 42.3 GB · IQ4_XS · tight 11.8 tok/s
- 04 L20 48 GB · needs 42.3 GB · IQ4_XS · tight 11.8 tok/s
- 05 Radeon PRO W7800 48 GB 48 GB · needs 42.3 GB · IQ4_XS · tight 9.2 tok/s
- 06 Radeon PRO W7900 48 GB · needs 42.3 GB · IQ4_XS · tight 9.2 tok/s
- 07 Data Center GPU Max 1100 48 GB · needs 42.3 GB · IQ4_XS · tight 10.9 tok/s
- 08 RTX 6000 Ada Generation 48 GB · needs 42.3 GB · IQ4_XS · tight 13.1 tok/s
- 09 L40 48 GB · needs 42.3 GB · IQ4_XS · tight 11.8 tok/s
- 10 L40S 48 GB · needs 42.3 GB · IQ4_XS · tight 11.8 tok/s
What the numbers mean
What you need to run it
Minimum card
Quadro RTX 8000
Memory needed
42.3 GB
Fastest
44.6 tok/s
InternVL2-Llama3-76B sits at 76B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 58 of the cards we track can hold it.
The least hardware that works is a Quadro RTX 8000. Its 48 GB is enough at IQ4_XS compression, giving roughly 9.2 tokens per second.
The quickest result comes from a B200 at around 44.6 tokens per second — its 8,000 GB/s of bandwidth is what buys that.
What this model is
InternVL2-Llama3-76B was published by Shanghai AI Lab, in China, in July 2024. It comes out of academia.
It works in Multimodal, Language, Vision, Video, and is recorded as doing visual question answering, Language modeling/generation, Question answering, Video description.
It is derived from Hermes 2 Theta Llama-3 70B,InternViT-6B rather than trained from scratch, which is the usual way a specialised model is produced.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. It is published under the OpenGVLab organisation on Hugging Face.
What decides the speed
The median result is around 14.3 tokens per second; 43 cards produce text faster than most people read it.
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.
Step by step
How to choose a GPU for InternVL2-Llama3-76B
The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.
-
01
Start from the memory column
The table lists every card that can hold InternVL2-Llama3-76B — around 42.3 GB at IQ4_XS. That figure, not the card's headline performance, is what decides whether it runs.
-
02
Decide how long your conversations run
The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context InternVL2-Llama3-76B can slip off a card that handles short questions easily.
-
03
Choose how far you will compress it
Each card runs the least-compressed copy it can hold — IQ4_XS on the smallest card that fits. Setting a floor drops the cards that only manage InternVL2-Llama3-76B by squeezing it further than you would want.
-
04
Compare tokens per second, not specifications
Sort by speed to see how cards rank for InternVL2-Llama3-76B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 44.6 tok/s.
-
05
Look at the headroom, not just the fit
A tight fit runs InternVL2-Llama3-76B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
-
06
See what else that card runs
Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for InternVL2-Llama3-76B alone — a card is usually bought for more than one model.
Answers
InternVL2-Llama3-76B — common questions
Would two GPUs run InternVL2-Llama3-76B faster?
A second card roughly doubles the memory available but not the generation rate. With 58 cards already able to run InternVL2-Llama3-76B alone, the case for pairing is weak.
Why does the quantisation differ between cards for InternVL2-Llama3-76B?
Each card is shown running the least-compressed copy it can hold, and InternVL2-Llama3-76B appears at 4 different compression levels across the cards that fit it. Bigger cards get the more accurate version.
How accurate are these InternVL2-Llama3-76B speed estimates?
Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 27–71 tok/s on the B200 rather than a single number.
What GPU do I need to run InternVL2-Llama3-76B?
The smallest card in our catalogue that holds InternVL2-Llama3-76B is the Quadro RTX 8000, with 48 GB of memory. It runs the model at IQ4_XS using about 42.3 GB, and produces roughly 9.2 tokens per second. 58 cards in total can run it.
How fast is InternVL2-Llama3-76B on a GPU?
It depends on the card. The quickest we calculate is a B200 at about 44.6 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 43 of the cards that can run InternVL2-Llama3-76B clear that.
How much VRAM does InternVL2-Llama3-76B need?
About 42.3 GB at IQ4_XS compression, 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.
Is InternVL2-Llama3-76B open source?
Its weights are published, so InternVL2-Llama3-76B 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.
How many parameters does InternVL2-Llama3-76B have?
InternVL2-Llama3-76B has 76B parameters. 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.
Who created InternVL2-Llama3-76B?
InternVL2-Llama3-76B was published by Shanghai AI Lab, based in China, categorised as academia.
When was InternVL2-Llama3-76B released?
InternVL2-Llama3-76B was published in July 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.
What is InternVL2-Llama3-76B used for?
InternVL2-Llama3-76B works in Multimodal, Language, Vision, Video, and is recorded as handling visual question answering, Language modeling/generation, Question answering, Video description. These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download InternVL2-Llama3-76B?
Its weights are published under the OpenGVLab organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.
Can I run InternVL2-Llama3-76B 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 InternVL2-Llama3-76B is rarely worth using — the nearest miss we calculate is short by 10.7 GB. Every figure here assumes the whole model is on the card.
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.