can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Pro (64GB) run Kimi Linear 48B-A3B (MoE)?

Kimi · MIT · estimated for a 64.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Kimi Linear 48B-A3B (MoE) at Q5_K_M · 35.1 GB · 61–92 tok/s on a MacBook Pro M5 Pro (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K17.5 GB90–134 tok/sRuns great
Q3_K_M22.7 GB79–118 tok/sRuns great
Q4_K_M30.1 GB67–101 tok/sRuns great
Q5_K_M35.1 GB61–92 tok/sRuns great
Q6_K40.5 GB56–84 tok/sTight / slow
Q8_052.3 GB47–70 tok/sWon't fit
FP1698.3 GB29–43 tok/sWon't fit

Ran Kimi Linear 48B-A3B (MoE) on a MacBook Pro M5 Pro (64GB)? Add your real numbers →