GPT-OSS 120B
GPT-OSS 120B loads in 65.4 GB at MXFP4 and decodes at the speed of its 5.1B active path, comfortably from 96 GB of memory — Macs included, starting at the MacBook Pro M5 Max 128GB. Below is the memory math we ran for it, the cheapest card that fits, and the fastest machine we track.
How much memory does GPT-OSS 120B need?
GPT-OSS 120B is a 117B mixture-of-experts model (5.1B active per token) built for reasoning, coding, agents. The weights alone take 65.4 GB at MXFP4; add context and the OS, and it belongs in the 96 GB memory class. Every number below comes from the ModelFit engine — speeds are estimates, labeled est., because we do not benchmark hardware ourselves.
KV = fp16 estimate (q8_0 cache roughly halves it). "Comfortable" = weights + KV within the engine's tiered budget (~70-85% of memory).
Which machines run GPT-OSS 120B?
Verdicts come from the same engine that powers our fit checker — memory capacity first, bandwidth for speed. How we compute these numbers · Hugging Face model card
Go deeper
More GPT-OSS models
Frequently asked questions
How much memory does GPT-OSS 120B need?
65.4 GB for the MXFP4 weights, plus ~6.0 GB of KV-cache at 16k context — about 71.4 GB total. Comfortable from 96 GB of VRAM or unified memory.
Does GPT-OSS 120B run on a Mac?
Yes — from the MacBook Pro M5 Max 128GB (~29 tok/s est.). Unified memory means the RAM budget is the only limit.
What is the cheapest GPU for GPT-OSS 120B?
The AMD Ryzen AI Max+ 395 (Strix Halo) is the cheapest tracked card that runs GPT-OSS 120B comfortably — ~11 tok/s est. at ~$3,847 used (as of 2026-07-31).
Which GPT-OSS 120B quant should I pick?
The tracked MXFP4 build at 65.4 GB is the one we recommend for most machines. Every published build, ranked by real GGUF file size rather than a formula, is on the quant comparison page linked below.
Cite this page
ModelFit: GPT-OSS 120B — specs, memory math and hardware verdicts. https://modelfit.io/models/gpt-oss-120b/ (dataset updated 2026-09-03, CC BY 4.0).