can-i-run-this-llm

Can I run this LLM?

Can a Mac mini M6 (24GB) run MiMo V2.6 Distill Qwen 9B?

MiMo · MIT · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: MiMo V2.6 Distill Qwen 9B at Q6_K · 7.8 GB · 13–20 tok/s on a Mac mini M6 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.6 GB26–39 tok/sRuns great
Q3_K_M4.5 GB22–33 tok/sRuns great
Q4_K_M5.8 GB17–26 tok/sRuns great
Q5_K_M6.9 GB15–22 tok/sRuns great
Q6_K7.8 GB13–20 tok/sRuns great
Q8_09.6 GB11–17 tok/sTight / slow
FP1617.9 GB6–9 tok/sWon't fit

Ran MiMo V2.6 Distill Qwen 9B on a Mac mini M6 (24GB)? Add your real numbers →