can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M3 Ultra (96GB) run GPT-OSS 120B (MoE)?

GPT-OSS · Apache 2.0 · estimated for a 96.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: GPT-OSS 120B (MoE) at FP16 · 65.4 GB · 87–130 tok/s on a Mac Studio M3 Ultra (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K62.6 GB88–133 tok/sTight / slow
Q3_K_M62.6 GB88–132 tok/sTight / slow
Q4_K_M62.8 GB88–132 tok/sTight / slow
Q5_K_M62.9 GB88–132 tok/sTight / slow
Q6_K63.3 GB88–132 tok/sTight / slow
Q8_063.4 GB88–132 tok/sTight / slow
FP1665.4 GB87–130 tok/sTight / slow
Open the full calculator →Everything a Mac Studio M3 Ultra (96GB) runsGPT-OSS 120B (MoE) on other machinesWhat to buy to run it →

Ran GPT-OSS 120B (MoE) on a Mac Studio M3 Ultra (96GB)? Add your real numbers →