can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run Hunyuan Hy3 (MoE)?

Hunyuan · Apache 2.0 · estimated for a 141.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Hunyuan Hy3 (MoE) at Q2_K · 97.1 GB · 199–298 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K97.1 GB199–298 tok/sRuns great
Q3_K_M128.9 GB177–265 tok/sWon't fit
Q4_K_M181.1 GB149–224 tok/sWon't fit
Q5_K_M212.9 GB136–205 tok/sWon't fit
Q6_K246.5 GB125–188 tok/sWon't fit
Q8_0317.5 GB106–160 tok/sWon't fit

Ran Hunyuan Hy3 (MoE) on a NVIDIA H200 (141GB)? Add your real numbers →