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 · 106.7 GB · 191–287 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K106.7 GB191–287 tok/sRuns great
Q3_K_M137.6 GB171–257 tok/sWon't fit
Q4_K_M182.2 GB149–223 tok/sWon't fit
Q5_K_M212.8 GB136–205 tok/sWon't fit
Q6_K257.3 GB122–183 tok/sWon't fit
Q8_0317.7 GB106–159 tok/sWon't fit
Open the full calculator →Everything a NVIDIA H200 (141GB) runsHunyuan Hy3 (MoE) on other machinesWhat to buy to run it →

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