A description (tagline) is not available for this product.
Leveraging the newest NVIDIA Blackwell and prior Ada Lovelace generation of GPUs, MojoGPU can power your business with better results than other providers because of it's use of premium enterprise hardware and fully optimized, high bandwidth networks. MojoGPU servers have amazing features which include selectable 1/5/10/25/50 gigabit networking, guaranteed storage IOP/s, RAID protected NVMe local storage, dedicated pinned CPUs, and dedicated memory space. Enjoy the generous included data transfer allowance of 324TB with its always low overage rate of $.50/TB, or achieve additional savings with plans up to 10 Petabytes. #ThatsGoodMojo
RTX 6000 ADA 48GB
Ada Lovelace Generation GPU
48 GB GDDR6 ECC VRAM
18,176 CUDA Cores
568 Tensor Cores (4th-gen)
142 RT Cores (3rd-gen)
960 GB/s Memory Bandwidth
~91.06 TFLOPS FP32 Performance
1,457 TOPS FP8/INT8 Performance
RTX Pro 6000 Max Q 24GB
Blackwell Generation GPU
24 GB GDDR7 ECC VRAM
6,016 CUDA Cores
188 Tensor Cores (5th-gen)
47 RT Cores (4th-gen)
448 GB/s Memory Bandwidth
~31.25 TFLOPS FP32 Performance
~1,000 TOPS FP8/INT8 Performance
RTX Pro 6000 Blackwell Max Q 48GB
Blackwell Generation GPU
48 GB GDDR7 ECC VRAM
12,032 CUDA Cores
376 Tensor Cores (5th-gen)
94 RT Cores (4th-gen)
896 GB/s Memory Bandwidth
~61.5 TFLOPS FP32 Performance
~2,000 TOPS FP8/INT8 Performance
RTX Pro 6000 Blackwell Max Q 96GB
Blackwell Generation GPU
96 GB GDDR7 ECC VRAM
24,064 CUDA Cores
752 Tensor Cores (5th-gen)
188 RT Cores (4th-gen)
1,792 GB/s Memory Bandwidth
~125 TFLOPS FP32 Performance
~4,000 TOPS FP8/INT8 Performance
