llamaperf
Submit

M2 8GB vs RTX 5090

For running local LLMs · 10 reports across 2 models

Side A
M2 8GB
Vendor
apple
VRAM
8GB
Memory
Unified
Side B
RTX 5090
Vendor
nvidia
VRAM
32GB
Memory
Discrete

Tokens per second by model

ModelM2 8GBRTX 5090
Qwen3.6up to 35B—3238.0n=7
Gemma 4up to 31B—578.0n=3

More comparisons