llamaperf

H100 80GB vs H200

For running local LLMs · 7 reports across 5 models

Side A
H100 80GB
Vendor
nvidia
VRAM
80GB
Memory
Discrete
Side B
H200
Vendor
nvidia
VRAM
141GB
Memory
Discrete

Highest reported generation speed by model family

These maxima come from different community setups. Model size, quantization, GPU count, offloading and concurrency may differ. They do not establish which GPU is faster for the same workload. Check the comparison conditions →

ModelH100 80GBH200
DeepSeek V4 Flashup to 285B193.0n=14.8n=2
Gemma 4up to 31B125.3n=1
HobbyLMup to 1Bn=1
Qwen3.5up to 122Bn=1
Qwen3.6up to 35B45.0n=1

More comparisons