can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M3 Pro (18GB) run GPT-OSS 20B (MoE)?

GPT-OSS · Apache 2.0 · estimated for a 18.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: GPT-OSS 20B (MoE) at Q3_K_M · 11.5 GB · 36–55 tok/s on a MacBook Pro M3 Pro (18GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.5 GB37–55 tok/sTight / slow
Q3_K_M11.5 GB36–55 tok/sTight / slow
Q4_K_M11.6 GB36–54 tok/sWon't fit
Q5_K_M11.7 GB36–54 tok/sWon't fit
Q6_K12.0 GB35–53 tok/sWon't fit
Q8_012.1 GB35–53 tok/sWon't fit
FP1613.8 GB32–48 tok/sWon't fit
Open the full calculator →Everything a MacBook Pro M3 Pro (18GB) runsGPT-OSS 20B (MoE) on other machinesWhat to buy to run it →

Ran GPT-OSS 20B (MoE) on a MacBook Pro M3 Pro (18GB)? Add your real numbers →