llamaperf

M4 Pro 48GB vs RX 7900 XTX

For running local LLMs · 16 reports across 7 models

Side A
M4 Pro 48GB
Vendor
apple
VRAM
48GB
Memory
Unified
Side B
RX 7900 XTX
Vendor
amd
VRAM
24GB
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 →

ModelM4 Pro 48GBRX 7900 XTX
Qwen3.8up to 2400B20.3n=172.1n=8
Museup to 30B18.0n=2
DeepSeek V4 Flashup to 285B12.0n=1
GLM-5.3up to 321B1.8n=1
Gemma 4up to 31Bn=1
LingBot-World-V2up to 1Bn=1
Qwen3.6up to 35Bn=1

More comparisons