can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run Gemma 4 26B-A4B (MoE)?

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

Yes — it runs great.

Best fit: Gemma 4 26B-A4B (MoE) at FP16 · 50.5 GB · 197–296 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M12.7 GB296–444 tok/sRuns great
Q4_K_M17.0 GB280–421 tok/sRuns great
Q5_K_M21.2 GB266–400 tok/sRuns great
Q6_K23.2 GB260–390 tok/sRuns great
Q8_026.9 GB249–374 tok/sRuns great
FP1650.5 GB197–296 tok/sRuns great

Ran Gemma 4 26B-A4B (MoE) on a NVIDIA H200 (141GB)? Add your real numbers →