What hardware do you need to run gpt-oss-120b?

gpt-oss-120b at MXFP4 is 63 GB of weights, with a context ceiling of 128k tokens. The best reasoning per gigabyte on this list. Needs about 64 GB and rewards it. On the cheapest machine that runs it, a Framework Desktop, 128GB, it generates 35 tok/s at 32k of context, measured.

How good is gpt-oss-120b, really?

On the Artificial Analysis Intelligence Index v4.3 it scores 12 (high reasoning effort; 10 at low), which puts it in the Below every hosted tier band. Fine for simple, well-specified tasks. Noticeably less capable than anything the big labs sell today. See the whole table.

• Summarising — good
• Translation — usable
• Everyday coding — good
• Reasoning & maths — good
• Agentic work — usable

Head to head with its neighbours on the leaderboard: vs Qwen3.5 4B above it, vs Ling 3.0 tiny below. One more model needs much the same memory at 32k of context: vs Llama 4 Scout 17B-16E.

What gpt-oss-120b costs either way

Renting the same model costs $0.03 per million input tokens and $0.15 per million output (OpenRouter, cheapest active endpoint, checked 2026-10-29). Buying a machine only beats that if you use it hard enough, for long enough, that the hardware price divides down below the rental bill. What a million tokens costs each way puts the two prices side by side.

Machines that run gpt-oss-120b

Every machine here holds it to 128k, this model's own ceiling, so the choice between them is speed and price rather than how much you can keep in the window.

The table is the cheapest machine in each family, not the only one that runs it: 19 of the 56 machines on this site hold it at 32k. Within a family only memory decides, so that is every Mac Studio and NVIDIA card with 96GB or more, every Strix Halo box and MacBook Pro with 128GB or more and the DGX Spark, 128GB. One table sets every machine against the others: price, the memory its GPU can use, what it holds and how long it takes to pay for itself.

One machine per family, cheapest first. Speeds are measured where a public benchmark exists and estimated from memory bandwidth otherwise; the calculator says which for any configuration. The longest context is the longest setting the calculator offers that the machine still holds this model at, cache included, and no machine is shown taking it past its own 128k limit. Each one opens the calculator on that machine at that length.

For scale, the calculator starts from 80 tok/s for a hosted API and times a local machine against it. 1 of the 5 above reaches it, and the slowest is 35 tok/s.

The cheapest machine that runs it is sold with 128 GB. There is a page on what 128 GB runs, machine by machine: it names the 11 machines here sold at that size, and the 39 current models the roomiest of them holds at 32k, this one among them.

It fits in less memory than that: the smallest size here that runs it at 32k is 96 GB, on the RTX PRO 6000 Blackwell, 96GB at $18,000, card only, which hands a model 95 GB.

Run gpt-oss-120b at 128k on the Strix Halo Framework Desktop, 128GB

How much memory does gpt-oss-120b need at 128k?

Every figure above is priced at 32k of context. At 128k, this model's own ceiling, gpt-oss-120b needs 68.2 GB rather than 64.6 GB. The weights are the same either way; the key-value cache goes from 1.2 GB to 4.8 GB.

The window costs nothing in hardware: the same 13 of the 37 machines here still sold at a published price hold gpt-oss-120b at both lengths, and the cheapest of them is the Framework Desktop, 128GB at $3,449.

On the Framework Desktop, 128GB it runs 35 tok/s measured at 32k and 18 tok/s measured at 128k. Every token generated reads the whole cache back, so a longer window is slower as well as bigger.

What has been measured running gpt-oss-120b

Three of the speeds in the table above were measured, and there are more measurements than that table shows. Seven machines here have a published speed for gpt-oss-120b. The table above has three of them; the other four are still sold but not the cheapest of their family. They are below, as published and again at 32k of context, which is what every other speed on this page is taken at.

A published figure is what its source reports, at the window the model was run at. The 32k figure is that measurement read at 32k of context: every token generated reads the weights and the whole key-value cache, so the longer the window the slower it runs. Each published figure links the source that took it.

The specifics

Parameters

116.8B, of which 5.1B are active per token

Quantisation

MXFP4

Weights on disk

63 GB

KV cache

1.2 GB at 32k context — Half the layers use a 128-token sliding window; KV cache is tiny. How weights and cache add up.

Maximum context

128k tokens

Licence

Apache 2.0

Sources

ggml-org/gpt-oss-120b-GGUF, openai/gpt-oss-120b