Calculator SubmitSign in

H100 80GB vs RTX 3090

For running local LLMs · 10 reports across 4 models

Side A

Vendor: nvidia
VRAM: 80GB
Memory: Discrete

Side B

Vendor: nvidia
VRAM: 24GB
Memory: Discrete

Tokens per second by model

Model	H100 80GB	RTX 3090
Qwen3.6up to 35B	45.0n=1	72.9n=6
Gemma 4up to 31B	125.3n=1	—
Qwen2.5	—	28.0n=1
Qwen3.5up to 27B	—n=1	—

More comparisons