can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M5 Ultra (256GB) run MiMo V2.6 Distill Qwen 9B?

MiMo · MIT · estimated for a 256.0 GB machine at 4K context.

Yes — it runs great.

Best fit: MiMo V2.6 Distill Qwen 9B at FP16 · 17.9 GB · 36–54 tok/s on a Mac Studio M5 Ultra (256GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.6 GB96–144 tok/sRuns great
Q3_K_M4.5 GB88–132 tok/sRuns great
Q4_K_M5.8 GB77–115 tok/sRuns great
Q5_K_M6.9 GB70–105 tok/sRuns great
Q6_K7.8 GB65–97 tok/sRuns great
Q8_09.6 GB57–86 tok/sRuns great
FP1617.9 GB36–54 tok/sRuns great

Ran MiMo V2.6 Distill Qwen 9B on a Mac Studio M5 Ultra (256GB)? Add your real numbers →