Skip to content
selfhostr
Open the menu

run a model

Running gpt-oss 120B

Fits on a single 80 GB card, or a Mac with a lot of unified memory.

120 billion parameterslicence : Apache 2.0weights ↗

memory needed

81.6 GB

Nothing in our catalogue has the memory for this one. That is the honest answer: at this size you are renting a machine by the hour, not buying one.

the alternatives

Apple Silicon, 128 GB unified96 GB usable

runs it, but only just

€7,659 · checked 2026-08-02product page ↗

Only just means it works, until the day you lengthen the context or open something else. Which is the day you conclude the tool lied to you.

not enough memory

if you change the format

4-bit weightswhat almost everyone runs, and what the hardware below is judged against
81.6 GB
8-bit weightsvisibly better on long or precise answers
146.4 GB
16-bit weightsthe model as it was trained, and rarely worth it at home
290.4 GB

Everything above assumes 4-bit weights and a 8k token context. Going up in precision costs memory; shortening the context is the other lever, and the cheaper one when something almost fits. Model details checked on 2026-08-02.

how to actually run it

Installing Ollama on your server→

what this page will not tell you

How many tokens per second you will get. That is a benchmark — it depends on memory bandwidth, on the engine, on the context and on how long the answers are. This site does not invent benchmarks, and everyone who quotes one for your exact setup is guessing.

builder

Price a whole machine around itA card is not a server. The builder adds the machine, the drives, the electricity and the backup.
every piece of hardware we size →