can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M4 Pro (48GB) run Kimi Linear 48B-A3B (MoE)?

Kimi · MIT · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Kimi Linear 48B-A3B (MoE) at Q3_K_M · 21.2 GB · 76–114 tok/s on a MacBook Pro M4 Pro (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K16.0 GB87–131 tok/sRuns great
Q3_K_M21.2 GB76–114 tok/sRuns great
Q4_K_M29.8 GB62–93 tok/sTight / slow
Q5_K_M35.0 GB56–84 tok/sWon't fit
Q6_K40.5 GB51–76 tok/sWon't fit
Q8_052.2 GB43–64 tok/sWon't fit
FP1698.2 GB26–39 tok/sWon't fit

Ran Kimi Linear 48B-A3B (MoE) on a MacBook Pro M4 Pro (48GB)? Add your real numbers →