can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air M2 (8GB) run MiMo V2.6 Distill Qwen 9B?

MiMo · MIT · estimated for a 8.0 GB machine at 4K context.

Yes — it runs great.

Best fit: MiMo V2.6 Distill Qwen 9B at Q2_K · 3.6 GB · 16–24 tok/s on a MacBook Air M2 (8GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.6 GB16–24 tok/sRuns great
Q3_K_M4.5 GB13–20 tok/sTight / slow
Q4_K_M5.8 GB11–16 tok/sWon't fit
Q5_K_M6.9 GB9–14 tok/sWon't fit
Q6_K7.8 GB8–12 tok/sWon't fit
Q8_09.6 GB7–10 tok/sWon't fit
FP1617.9 GB4–5 tok/sWon't fit

Ran MiMo V2.6 Distill Qwen 9B on a MacBook Air M2 (8GB)? Add your real numbers →