GPU VRAM calculator

Run gpt-oss-120b locally: hardware requirements

gpt-oss-120b needs about 67.2 GB of GPU memory for one person at 32K context, and about 4.5 GB more for each extra person at 64K. For 80 users working as AI agents, plan on 137 GB, which fits one B200.

OpenAI, United States. 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: openai/gpt-oss-120b

On Hugging Face

OpenAI, United States · 117B parameters · License: apache-2.0

What you need for 16 active users

1 × B200

It holds the model and up to 23 active users at 64K context.

The server

384 GB RAM
48 CPU cores
500 GB NVMe

Rules of thumb

GPU memory in total
137 GB
Weights
65.2 GB (published files)
Conversation cache, all active
72.0 GB
Engine (vLLM)
3.0 GB

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. 5 cards too small for this model are left out.

CardMemoryActive users, one serverFor your 16 active
B200180 GB231 × B200
A10080 GB192 × A100
H10080 GB192 × H100
H200 NVL141 GB452 × H200 NVL
L40S48 GB264 × L40S
RTX 4000 Ada20 GB28 servers, each with 4 × RTX 4000 Ada
RTX 6000 Ada48 GB264 × RTX 6000 Ada
RTX A500024 GB54 servers, each with 4 × RTX A5000
RTX PRO 4000 Blackwell24 GB54 servers, each with 4 × RTX PRO 4000 Blackwell
RTX PRO 4500 Blackwell32 GB122 servers, each with 4 × RTX PRO 4500 Blackwell
RTX PRO 5000 Blackwell48 GB264 × RTX PRO 5000 Blackwell
RTX PRO 6000 Blackwell96 GB262 × RTX PRO 6000 Blackwell

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.

gpt-oss-120b by team size

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

Total usersAt onceGPU memoryWhat you need
20483.0 GB1 × RTX PRO 6000 Blackwell
8016137 GB1 × B200
12024173 GB2 × RTX PRO 6000 Blackwell
500100515 GB4 × H200 NVL

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 gpt-oss-120b need?

gpt-oss-120b needs about 67.2 GB of GPU memory for one person at 32K context, and about 4.5 GB more for each extra person at 64K. For 80 users working as AI agents, plan on 137 GB, which fits one B200.

How many active users can gpt-oss-120b handle on one 96 GB GPU?

By memory, about 5 active users at once at 64K context on a card such as the RTX PRO 6000 Blackwell. Speed can set a lower limit, so load-test before you buy.

Can gpt-oss-120b run on a 24 GB GPU such as the RTX 4090?

Not as published for one person at 32K context: it needs about 67.2 GB. A 4-bit or 8-bit build may fit, if the model has one.

What license does gpt-oss-120b use?

Hugging Face lists its license as apache-2.0. 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