can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M3 Ultra (512GB) run Hunyuan Hy3 (MoE)?

Hunyuan · Apache 2.0 · estimated for a 512.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Hunyuan Hy3 (MoE) at Q8_0 · 317.7 GB · 21–31 tok/s on a Mac Studio M3 Ultra (512GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K106.7 GB46–69 tok/sRuns great
Q3_K_M137.6 GB39–58 tok/sRuns great
Q4_K_M182.2 GB32–48 tok/sRuns great
Q5_K_M212.8 GB28–42 tok/sRuns great
Q6_K257.3 GB24–37 tok/sRuns great
Q8_0317.7 GB21–31 tok/sRuns great

Ran Hunyuan Hy3 (MoE) on a Mac Studio M3 Ultra (512GB)? Add your real numbers →