Sunk Cost sunkcost.ai Data checked 2026-09-03

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.

Cheapest machine that runs itStrix Halo Framework Desktop, 128GB at $3,449
Fastest of the ones listedMac Studio M5 Ultra, 96GB — 90 tok/s at 32k context
Honest answer on costPays back in 687 years at 500k tokens a day.

How good is it, 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. Score source. See the whole table.

What it costs either way

Renting the same model costs $0.03 per million input tokens and $0.17 per million output (OpenRouter, cheapest active endpoint, checked 2026-09-03). 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.

Machines that run it

MachinePriceSpeed at 32kPay-back
Strix Halo Framework Desktop, 128GB $3,449 35 tok/s measured Pays back in 687 years Run the numbers
DGX Spark GB10 Grace Blackwell, 128GB $4,699 41 tok/s measured Pays back in 922 years Run the numbers
Mac Studio M5 Max, 128GB $5,099 46 tok/s estimated Pays back in 946 years Run the numbers
MacBook Pro M5 Max (16-inch), 128GB $6,999 46 tok/s estimated Pays back in 1,299 years Run the numbers

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 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.
Maximum context
128k tokens (128k)
Licence
Apache 2.0
Sources
source 1, source 2