M1 8GB vs RTX 5090

For running local LLMs · 9 reports across 2 models

Side A

Vendor: apple
VRAM: 8GB
Memory: Unified

Side B

Vendor: nvidia
VRAM: 32GB
Memory: Discrete

Tokens per second by model

Model	M1 8GB	RTX 5090
Qwen3.6up to 35B	—	215.1n=6
Gemma 4up to 31B	17.5n=1	578.0n=2

More comparisons