can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M4 Pro (48GB) run GPT-OSS 20B (MoE)?

GPT-OSS · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GPT-OSS 20B (MoE) at FP16 · 13.8 GB · 50–76 tok/s on a MacBook Pro M4 Pro (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.5 GB57–85 tok/sRuns great
Q3_K_M11.5 GB57–85 tok/sRuns great
Q4_K_M11.6 GB56–84 tok/sRuns great
Q5_K_M11.7 GB56–84 tok/sRuns great
Q6_K12.0 GB55–83 tok/sRuns great
Q8_012.1 GB55–82 tok/sRuns great
FP1613.8 GB50–76 tok/sRuns great

Ran GPT-OSS 20B (MoE) on a MacBook Pro M4 Pro (48GB)? Add your real numbers →