llamaperf

RTX Pro 6000 Blackwell vs RTX PRO 6000 Max-Q

For running local LLMs · 31 reports across 8 models

Side A
RTX Pro 6000 Blackwell
Vendor
nvidia
VRAM
96GB
Memory
Discrete
Side B
RTX PRO 6000 Max-Q
Vendor
nvidia
VRAM
96GB
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 BlackwellRTX PRO 6000 Max-Q
Qwen3.8up to 2400B177.0n=13240.0n=2
DeepSeek V4 Flashup to 285B45.0n=444.0n=1
Qwen3.6up to 35Bn=4
DeepSeek V4 Pro7.1n=2
Museup to 30B57.0n=2
Llama 3.2up to 1Bn=1
Mimo 2.5n=1
Tencent-HY3up to 295B57.4n=1

More comparisons