can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M3 Ultra (96GB) run MiMo V2.6 Distill Qwen 9B?

MiMo · MIT · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: MiMo V2.6 Distill Qwen 9B at FP16 · 17.9 GB · 26–39 tok/s on a Mac Studio M3 Ultra (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.6 GB79–119 tok/sRuns great
Q3_K_M4.5 GB71–106 tok/sRuns great
Q4_K_M5.8 GB60–90 tok/sRuns great
Q5_K_M6.9 GB54–81 tok/sRuns great
Q6_K7.8 GB50–74 tok/sRuns great
Q8_09.6 GB43–64 tok/sRuns great
FP1617.9 GB26–39 tok/sRuns great

Ran MiMo V2.6 Distill Qwen 9B on a Mac Studio M3 Ultra (96GB)? Add your real numbers →