GPU Comparison

AMD Radeon AI PRO R9700 vs NVIDIA RTX PRO 4000 SFF Blackwell

How the AMD Radeon AI PRO R9700 and NVIDIA RTX PRO 4000 SFF Blackwell compare across memory, compute, power and form factor, with the stronger figure highlighted on each row. Vendor-specific figures (CUDA vs stream processors, Tensor vs matrix cores) are listed on their own rows.

Specification	RDNA 4 AMD Radeon AI PRO R9700 NVIDIA alternative: NVIDIA RTX PRO 4500 Blackwell Workstation Edition →	BLACKWELL NVIDIA RTX PRO 4000 SFF Blackwell View Product →
Pricing
Price	Not sold by NVNexus	$2,925.60
Overview
Architecture	AMD RDNA 4	Blackwell
Memory
Memory	32 GB GDDR6	24 GB GDDR7 with ECC
Memory Bandwidth	640 GB/s	432 GB/s
Memory Interface	256-bit	192-bit
Compute
CUDA Cores	–	8,960
Stream Processors (AMD)	4,096 (64 CUs)	–
Tensor Cores	–	280 (5th Gen)
Matrix Cores / AI Accelerators (AMD)	128 AI accelerators	–
RT Cores / Ray Accelerators	64 ray accelerators	70 (4th Gen)
FP32	47.8 TFLOPS	24 TFLOPS
FP16/BF16 Tensor	95.7 TFLOPS	–
Tensor / AI Performance	Up to 1,531 TOPS (INT4 sparse)	770 TOPS (FP4 Sparse)
RT Performance	–	73 TFLOPS
Platform
Interface	PCIe 5.0 x16	PCIe 5.0 x8
TDP	300W	70W (no external power)
Form Factor	Dual-slot, active (blower)	2.7" H x 6.6" L, HHHL Dual Slot
Display Outputs	4x DisplayPort 2.1a	4x Mini DisplayPort 2.1b

Not sure which fits?

Talk it through with a specialist

Tell us your workload and we will recommend the right GPU, configuration, and sourcing options.

Talk to an Expert →

Talk it through with a specialist

More Comparisons