llamaperf
Submit

M5 Max 48GB vs RTX 5090

For running local LLMs · 65 reports across 11 models

Side A
M5 Max 48GB
Vendor
apple
VRAM
48GB
Memory
Unified
Side B
RTX 5090
Vendor
nvidia
VRAM
32GB
Memory
Discrete

Highest reported generation speed by model family

These maxima come from different community setups. Model size, quantization, GPU count, offloading and concurrency may differ. They do not establish which GPU is faster for the same workload. Check the comparison conditions →

ModelM5 Max 48GBRTX 5090
Qwen3.8up to 2400B—220.0n=35
DeepSeek V4 Flashup to 285B—120.0n=10
Qwen3.6up to 35B—215.1n=6
Gemma 4up to 31B—578.0n=4
Museup to 30B—253.0n=4
GLM-5.2up to 744B——n=1
GLM-5.3up to 321B—24.5n=1
Kimi K2.5——n=1
Qwen2.5up to 32B——n=1
Qwen3up to 235B—159.0n=1
Qwen3.5up to 122B——n=1

More comparisons