llamaperf

RTX PRO 6000 Max-Q vs RX 7900 XTX

For running local LLMs · 16 reports across 5 models

Side A
RTX PRO 6000 Max-Q
Vendor
nvidia
VRAM
96GB
Memory
Discrete
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 →

ModelRTX PRO 6000 Max-QRX 7900 XTX
Qwen3.8up to 2400B240.0n=272.1n=8
DeepSeek V4 Flashup to 285B44.0n=112.0n=1
DeepSeek V4 Pro7.1n=2
Gemma 4up to 31Bn=1
Qwen3.6up to 35Bn=1

More comparisons