M1 8GB vs RTX 5080

For running local LLMs · 2 reports across 2 models

Side A

Vendor: apple
VRAM: 8GB
Memory: Unified

Side B

Vendor: nvidia
VRAM: 16GB
Memory: Discrete

Tokens per second by model

Model	M1 8GB	RTX 5080
Gemma 4up to 31B	17.5n=1	—
Qwen3.6up to 35B	—	56.0n=1

More comparisons