Run gpt-oss-120b on-premises
○ Memory-fit arithmetic — checkable math, not a benchmark
gpt-oss-120b is OpenAI's open-weight flagship: about 117 billion total parameters with ~5.1 billion active per token (mixture-of-experts), released under the permissive Apache-2.0 license and shipped in a native MXFP4 4-bit format. It is designed to run on a single high-memory accelerator, which makes it one of the most comfortable big-model fits for a 128 GB machine.
Here is the arithmetic against a machine with 128 GB of memory.
Memory fit in 128 GB
| Parameters | 117B total, ~5.1B active per token (MoE) |
|---|---|
| Native format | MXFP4 (~4-bit) — the format it ships in |
| Weights in memory | ~63 GB |
| Reference memory | 128 GB (one machine) |
| Left for context cache + system | roughly 45–55 GB |
| Fits in 128 GB | yes |
Because gpt-oss-120b ships in MXFP4, the ~63 GB weight figure is the format's own footprint, not an aggressive down-quantization — a 128 GB machine runs it with generous context headroom.
What it serves well
- General reasoning and tool-use / agentic workflows on your own hardware.
- A strong default 'house model' behind chat UIs and coding agents on your machine.
- Workloads where an Apache-2.0 license removes commercial-use friction entirely.
Honest limits
- This page is memory arithmetic, not a benchmark; we size the machine for your workload during the AI diagnostic.
- MoE models trade some raw depth for serving efficiency; whether that suits your task is something we test in the assessment rather than assert here.
Frequently asked questions
Does gpt-oss-120b fit in 128 GB of memory?
Yes, comfortably: in its native MXFP4 format the weights are ~63 GB against 128 GB, leaving tens of gigabytes for context and system.
What license is it under?
Apache-2.0 — a permissive license with no commercial-use restriction, which is part of why it is a strong default for a business machine.
Where does the ~63 GB figure come from?
From the format it ships in: ~117B parameters at roughly half a byte each in MXFP4. The exact footprint depends on the serving runtime; we confirm it for your setup during the AI diagnostic.
Find out which model fits your work
An AI diagnostic maps your processes, classes what is sensitive and sizes the model and the hardware against your real tasks.