can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Pro (64GB) run MiMo V2.6 Distill Qwen 9B?

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

Yes — it runs great.

Best fit: MiMo V2.6 Distill Qwen 9B at Q8_0 · 9.6 GB · 19–29 tok/s on a MacBook Pro M5 Pro (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.6 GB42–62 tok/sRuns great
Q3_K_M4.5 GB36–53 tok/sRuns great
Q4_K_M5.8 GB29–43 tok/sRuns great
Q5_K_M6.9 GB25–38 tok/sRuns great
Q6_K7.8 GB23–34 tok/sRuns great
Q8_09.6 GB19–29 tok/sRuns great
FP1617.9 GB11–16 tok/sTight / slow

Ran MiMo V2.6 Distill Qwen 9B on a MacBook Pro M5 Pro (64GB)? Add your real numbers →