Can GPT-OSS 20B run on Mac mini M6 16GB?

NO — Won’t fit
MXFP4 · 4K context · formula estimate

What this means

The checked MXFP4 build needs about 15GB, above this Mac's conservative 13GB working budget.

−2GB short
above the working budget
15GB
needed at MXFP4
MXFP4
quant selected
0GB
working headroom
needs 15 GBworking budget 13 GB · short 2 GB
Apple M616 GB unified memoryMetalActive cooling

Where the memory goes

ComponentDetailGB
Model weightsMXFP4 GGUF (12.1 GB) + mmap overhead12.7
KV cache4K context window1.5
RuntimemacOS inference app + compute buffers0.8
Total neededat MXFP4, 4K context15
Working budget16 GB unified memory − conservative macOS reserve13
Headroommemory shortfall−2

Pick your quant

QuantDownloadMemoryEstimated speedVerdict
MXFP412.1 GB15 GB Won't fit

Other models on this Mac

GPT-OSS 20B on other Mac mini M6 configurations

FAQ

Can the Mac mini M6 · 16GB run GPT-OSS 20B?

Not with the quants currently tracked. The selected MXFP4 build needs about 15GB, above the 13GB working budget.

Which GPT-OSS 20B quant should I use on this Mac?

None of the tracked quants fit this configuration safely. Choose a smaller model or a Mac with more unified memory.

Which app should I use for GPT-OSS 20B on this Mac?

Start with LM Studio. This page gives the complete point-and-click walkthrough.

Are these speeds measured on a Mac mini M6?

No. The range is a formula estimate based on memory bandwidth, model size, active parameters, cooling, and a 4K context. The app, backend, thermals, and prompt can change real performance.