Calculator SubmitSign in

H100 80GB vs M3 Max 128GB

For running local LLMs · 4 reports across 3 models

Side A

Vendor: nvidia
VRAM: 80GB
Memory: Discrete

Side B

Vendor: apple
VRAM: 128GB
Memory: Unified

Tokens per second by model

Model	H100 80GB	M3 Max 128GB
Qwen3.6up to 35B	45.0n=1	5.5n=1
Gemma 4up to 31B	125.3n=1	—
Qwen3.5up to 27B	—n=1	—

More comparisons