How many users per GPU? Our numbers, machine by machine

Updated: November 2026

How many users per graphics card?
From 3 to 15, depending on the card and the model.

A 16 GB RTX 5060 Ti supports 1 to 5 users simultaneously. An RTX 5090 supports 1 to 15. An RTX PRO 6000 supports 8 to 15 on a much larger model. With 4 cards, you can accommodate around forty users.

These figures are taken from our data sheets and comparisons. We have grouped them here, machine by machine, based on estimated capacities. These are benchmarks for sizing your machine, not speed measurements or guarantees.

Calculation Basisactive users at the same time
Context8,000 tokens on most lines
Configurationthe base configuration for each machine
capacity = card memory + model size + context length
There is no single valid figure for a card alone. The number of users only makes sense for a specific model.


Complete table, machine by machine

Machine Cards Memory Reference Model Simultaneous Users Price excl. VAT
CoreIA RTX 5060 Ti 116 GB8 billion parameters 1 à 5€1,724
CoreIA Radeon AI PRO R9700132 GB8 to 14 billion, text and RAG only 1 à 12€3,469
CoreIA RTX 5090132 GB8 to 14 billion 1 à 15€8,576
CoreIA RTX PRO 6000196 GB 70 billion8 to 15€20,494
CoreIA 2x RTX 5090 264 GB30 billion20 to 30€17,462
CoreIA 2x RTX PRO 6000 2 192 GB 70 billion 20 à 35€40,423
CoreIA Threadripper PRO 4 GPU1 to 496 to 384 GB 70 billion 8 to 15 with 1 card, around forty with 4 Max-Q cards €27,206
for 1 card
EPYC 8 GPU AI Server 4 à 8384 to 768 GB70 to 180 billion 50 à 200 €171,791
with 4 cards

Our November 2026 comparison figures are based on base configurations with a 8,000 token context for most lines. These figures change according to the options selected in the configurator. Base configuration prices are shown excl. VAT and are automatically updated from our shop.

The R9700 does not support CUDA. It is designed exclusively for text processing and document retrieval (RAG). Its performance specifications do not apply to image or video generation.

Machines with pricing based on the selected graphics card

On these two servers, the number of users varies depending on the graphics cards selected in the configurator. Their base configuration includes a R9700 with 32 GB.

MachineMemory by graphics cardSimultaneous usersBase price excl. VAT
Serveur IA PME EPYC 4005, 1 card32 or 96 GB 1 à 15€6,511
4U Rack AI Server, 1 or 2 cards32 to 192 GB 1 à 20€4,694

Machines built for large models, not for teams

MachineMemoryReference ModelSimultaneous usersPrice excl. VAT
CoreIA GB10128 GB of unified memory 70 billion 1 à 4€5,833
EPYC AI Server 768 GB96 GB per card, plus up to 768 GB of system memoryLarge model, in system memory 2 à 5On quote

While their memory capacity is vast, it is slower than that of a graphics card. They are designed to load what others cannot, meaning they serve fewer users simultaneously.


The figure per card

Here is the same table, scaled down to a single card. The final column is a simple division of our figures, not a measurement.

MachineReference ModelGraphics CardsPeopleBy graphics card
CoreIA RTX 5060 Ti8 billion 11 to 51 to 5
CoreIA RTX 5090 8 to 14 billion 1 1 to 15 1 to 15
CoreIA 2x RTX 5090 30 billion 2 20 to 30 10 to 15
CoreIA RTX PRO 6000 70 billion 1 8 to 15 8 to 15
CoreIA 2x RTX PRO 6000 70 billion 2 20 to 35 10 to 17
CoreIA Threadripper PRO 4 GPU 70 billion 4 Max-Q Around forty About 10
Key takeaways. On these machines, a single large graphics card supports approximately 15 people simultaneously. The EPYC 8 GPU AI Server is not included in this table: it is configured with 4 to 8 cards for a single range of 50 to 200 people, so a division would not be meaningful.
NVIDIA GeForce RTX 5090 32 GB graphics card
RTX 509032 GB, 1 to 15 people.
AMD Radeon AI PRO R9700 32 GB Graphics Card
Radeon AI PRO R970032 GB, 1 to 12 people, text and RAG.
NVIDIA RTX PRO 6000 Blackwell 96 GB graphics card
RTX PRO 600096 GB, 8 to 15 people, large model.


Why the RTX PRO 6000 does not serve more users than an RTX 5090

This is the most common misconception. The RTX PRO 6000 has three times as much memory as the RTX 5090, yet the number of concurrent users is similar. However, these two lines refer to different model sizes:

  • RTX 5090 : 1 to 15 users on an 8 to 14 billion parameter model;
  • RTX PRO 6000 : 8 to 15 users on a 70 billion parameter model.

The model running on the RTX PRO 6000 is 5 to 9 times larger. Therefore, the extra memory is used to load a more capable model, not to accommodate more users. If your workflow fits within a smaller model, a larger card will not provide more available seats.

The same logic applies to the GB10: 128 GB of memory, but only 1 to 4 users on a 70 billion parameter model. It is designed to load very large models. Its memory capacity is not intended for serving a large team.


What drives these numbers

Model size

The larger the model, the more memory it occupies, leaving less for active conversations. Consequently, all our figures refer to the reference model.

Context length

Context is the text the model keeps in mind to answer. Our figures assume 8,000 tokens, a token being a piece of a word. Each ongoing conversation takes up memory for its context. If your colleagues send entire files, the number of people decreases. Our VRAM calculator has a "simultaneous sessions" setting to test your case.

Searching your documents

RAG sends excerpts of your documents to the model, which are added to the context. Count it in your use. To learn more, read our article on the AI station with integrated RAG.

The number of cards

Two cards give more memory, and more throughput when several people query the machine at the same time. They do not make a single answer twice as fast. The details are in our multi-GPU guide.


Sizing in four steps

1. Count the people active at the same time

Not your headcount. Everyone does not write at the same time. Look at the busiest time of your day.

2. Choose the model

Try the smallest that does the job. It is what sets the required memory.

3. Read the line in the table

Take the bottom of the range if your documents are long, the top if the exchanges are short.

4. Keep a margin

Uses add up after installation. A machine sized just right is the one we replace the fastest. If you are not sure, describe your use to us: we size it in the quote.

What we do not publish. You will not find any speed in tokens per second here. It depends on the model, the engine, and the settings. An isolated figure would be misleading. The number of people in this article are orders of magnitude.


Our machines by number of people

They are assembled by hand in Auriol (13), except the GB10 assembled by ASUS. The assembly takes 15 business days maximum, often less, then comes the transport. 2-year warranty, extendable to 3 or 5 years, except the GB10.

Radiance CoreIA RTX 5060 Ti 1 to 5 users: CoreIA RTX 5060 Ti16 GB, 8B parameter model. €1,724 excl. VAT Radiance CoreIA RTX 5090 1 to 15 users: CoreIA RTX 509032 GB, 8B to 14B parameter model. €8,576 excl. VAT Radiance CoreIA 2x RTX PRO 6000 20 to 35 users: CoreIA 2x RTX PRO 6000192 GB, 70B parameter model. €40,423 excl. VAT Radiance AI Server EPYC 8 GPU 50 to 200 users: EPYC 8 GPU AI Server384 to 768 GB, 70B to 180B parameter model. €171,791 excl. VAT

Tell us your team size

Staff size, documents, and use cases: we provide a perfectly sized hardware and software configuration. Free, no-obligation quote, with a response within 24 working days.


FAQ

How many users can one graphics card serve?
Based on our benchmarks, from 1 to 15 people simultaneously. An RTX 5060 Ti supports 1 to 5 people on an 8B parameter model. An RTX 5090 supports 1 to 15 on an 8 to 14B model. An RTX PRO 6000 supports 8 to 15 on a 70B model.

How many users for a 4 GPU server?
Our workstation equipped with 4 RTX PRO 6000 Max-Q cards supports up to about forty people at the same time on a 70B model. Our EPYC server, featuring 4 to 8 cards, serves 50 to 200 people on a 70 to 180B model.

Is the number of users the same as the number of accounts?
No. Our figures count active users at any given moment. There is no software limit on the number of accounts. Therefore, a machine can host more accounts than there are concurrent users.

Does doubling the cards double the number of users?
Roughly so, according to our data. On 2-card machines: 8 to 15 people with one RTX PRO 6000, 20 to 35 with two. With 4 cards, we reach about forty, which is approximately 10 per card. This gain comes from throughput and memory, not from faster individual response times.

Why does the GB10 serve so few people with 128 GB?
Its memory is vast, but slower than that of a graphics card. It loads very large models for a small team: 2 to 4 people on a 70-billion-parameter model.

Are these figures guaranteed?
No. These are orders of magnitude for the base configuration, with a context of 8,000 tokens on most lines. They vary depending on the model, the length of the documents, and the usage. For sizing tailored to your case, describe your project to us.

Sources: data sheets and comparisons of the Radiance Systems range, November 2026. The divisions per card are a reading calculation. Values vary depending on the model, the inference engine, and the settings.

Free appointment · 30 minutes

Let’s talk about your local AI project

By phone or video call, we look at what you need together. You leave with a clear recommendation, with no commitment.

  • The AI computer or server that fits your use and your team
  • What we should develop for you, if needed: automations, applications, search in your documents
  • Budget and lead times, with a quote within 24 hours

Calls in English, French or Dutch.

Call language
Format
Choose a time slot Paris time

Loading time slots…

Back to the blog

Get your custom AI solution quote within 24 hours

Every Radiance project begins with a conversation. Fill out this form and an expert will respond promptly with a solution tailored to your business and budget.

Response within 24 working days
Delivery throughout Europe (EU)
2-year warranty included
On-site installation possible
No commitment required
Dedicated support before and after purchase
contact@radiancesystems.eu
+33 4 65 84 48 21
Monday, Tuesday, Thursday, and Friday from 9:00 to 17:00. Wednesday from 9:00 to 12:00. Saturday from 14:00 to 17:00.
01Are you looking for something?
Single choice. The following questions adapt to your response.
00What are you going to do with it?
Multiple choices possible.
00How many people are going to use it?
00What format?
00Do you already have an idea of the configuration?
Optional. Fill in what you know, leave "Advise me" for the rest.
If you leave everything on "Advise me," we will suggest a configuration based on your usage and budget.
00What are we installing?
Multiple choices possible.
00How many machines?
00Would you like help with the setup?
00Your profession / sector
Pre-filled if you are coming from a business tab on the page.
00What would you like to automate or accelerate?
In a few lines, in your own words. No need for technical vocabulary.
00Your organization
00How many people will use the tool?
00What should the tool be based on?
Multiple choices available. We start from your existing documents.
00What is your estimated budget?
00When do you need it?
00Delivery country (EU and Switzerland) *
We deliver throughout the European Union and Switzerland.
00Additional information (optional)
Noise constraints, format constraints, existing equipment, questions...
00How would you prefer us to reply to you?
If you choose "by email," you will be able to reply to our message to ask your questions and refine the quote.
00Email *
We will send the quote to this address.

Any more questions?

Email us at contact@radiancesystems.eu or reach out via the contact form; we respond to all inquiries within 3 hours during business hours (Monday, Tuesday, Thursday, and Friday from 9:00 to 17:00, Wednesday from 9:00 to 12:00, Saturday from 14:00 to 17:00).

📞 +33 4 65 84 48 21