GPT-OSS 20B
GPT-OSS 20B loads in 13.8 GB at MXFP4 and decodes at the speed of its 3.6B active path, comfortably from 32 GB of memory — Macs included, starting at the MacBook Air M5 24GB. 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 20B need?
GPT-OSS 20B is a 21B mixture-of-experts model (3.6B active per token) built for chat, coding, reasoning. The weights alone take 13.8 GB at MXFP4; add context and the OS, and it belongs in the 32 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 20B?
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 20B need?
13.8 GB for the MXFP4 weights, plus ~4.0 GB of KV-cache at 16k context — about 17.8 GB total. Comfortable from 32 GB of VRAM or unified memory.
Does GPT-OSS 20B run on a Mac?
Yes — from the MacBook Air M5 24GB (~25 tok/s est.). Unified memory means the RAM budget is the only limit.
What is the cheapest GPU for GPT-OSS 20B?
The AMD Radeon RX 7900 XT is the cheapest tracked card that runs GPT-OSS 20B comfortably — ~62 tok/s est. at ~$550 used.
Which GPT-OSS 20B quant should I pick?
The tracked MXFP4 build at 13.8 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 20B — specs, memory math and hardware verdicts. https://modelfit.io/models/gpt-oss-20b/ (dataset updated 2026-09-03, CC BY 4.0).