NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition vs NVIDIA RTX PRO 6000 Blackwell Server Edition

Both GPUs launched in 2025: the RTX PRO 6000 Blackwell Max-Q Workstation Edition on Blackwell and the RTX PRO 6000 Blackwell Server Edition on Blackwell.

Dense throughput for the RTX PRO 6000 Blackwell Max-Q Workstation Edition against the RTX PRO 6000 Blackwell Server Edition: FP32 110 vs 120 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 96 GB against 96 GB, fed at 1.8 TB/s versus 1.6 TB/s. More memory per GPU means larger models fit before you have to shard across cards, which often matters more than raw TFLOPS for inference.

Power budgets are 300 W for the RTX PRO 6000 Blackwell Max-Q Workstation Edition and 600 W for the RTX PRO 6000 Blackwell Server Edition. At FP32 that works out to 0.37 against 0.20 TFLOPS per watt.

For LLM training and inference, weight the FP8 and FP16 rows and memory capacity most heavily. For scientific and HPC workloads, the FP64 row is the one to read.