GPU VRAM calculator

Run DeepSeek-R1 locally: hardware requirements

DeepSeek-R1 needs about 711 GB of GPU memory for one person at 32K context, and about 107 GB more for each extra person at 64K. For 80 users working as AI agents, plan on 3680 GB, which takes 3 servers, each with 8 × B200.

DeepSeek, China. From its files on Hugging Face, checked 2026-11-05.

Context per person: more context lets the model work with longer conversations and more files, and needs more GPU memory for every person. As a guide: 8K for short chat, 32K for chat over documents, 64K for AI agents, whose instructions, tools and files all count.

80 users means about 16 people working at the same moment. That share is a planning assumption; if you know yours, choose the total that matches it.

Work it out for your team: deepseek-ai/DeepSeek-R1

On Hugging Face

DeepSeek, China · 684B parameters · License: mit

What you need for 16 active users

3 servers, each with 8 × B200

Each server runs its own copy of the model and holds 6 active users at 64K context.

Each server

3 TB RAM
64 CPU cores
2 TB NVMe

Rules of thumb

GPU memory in total
3680 GB
Weights, each server
689 GB (published files)
Conversation cache, all active
1708 GB
Engine (vLLM), each server
3.0 GB

Ways to need less

Your options by card

80 users means about 16 using the model at any moment. The others are not waiting; they are simply doing something else. If more become active than a build handles, they queue. 15 cards too small for this model are left out.

CardMemoryActive users, one serverFor your 16 active
B200180 GB63 servers, each with 8 × B200
H200 NVL141 GB36 servers, each with 8 × H200 NVL

These are memory limits. A card can hold more people than it can answer quickly, so test your own workload before you buy. More than one card in a server needs an engine that splits the model.

DeepSeek-R1 by team size

AI agents, 1 user in 5 active at a time, 64K context, as published.

Total usersAt onceGPU memoryWhat you need
2041085 GB7 × B200
80163680 GB3 servers, each with 8 × B200
120245191 GB4 servers, each with 8 × B200
50010021845 GB17 servers, each with 8 × B200

All models

How this is worked out

GPU memory = weights + a conversation cache for each person + the serving engine, from this model's files on Hugging Face. These are memory limits, not speed. The full method and its limits.

Questions

How much GPU memory does DeepSeek-R1 need?

DeepSeek-R1 needs about 711 GB of GPU memory for one person at 32K context, and about 107 GB more for each extra person at 64K. For 80 users working as AI agents, plan on 3680 GB, which takes 3 servers, each with 8 × B200.

How many active users can DeepSeek-R1 handle on one 96 GB GPU?

DeepSeek-R1 does not fit on one 96 GB card such as the RTX PRO 6000 Blackwell at 64K context. Compare larger cards or a smaller precision above.

Can DeepSeek-R1 run on a 24 GB GPU such as the RTX 4090?

Not as published for one person at 32K context: it needs about 711 GB. A 4-bit or 8-bit build may fit, if the model has one.

What license does DeepSeek-R1 use?

Hugging Face lists its license as mit. Check the license on the model's page before you use it.

Running a model on your own servers?

NeueCode is private autonomous intelligence for enterprise: it takes on your organization's tasks on your own GPUs, with nothing leaving your network, a person approving every action, and all of it on record. It runs each model on one card, so read the single-card figures above.

What you need to run NeueCode