Side-by-side, with the numbers that matter.

Two rigs, one table. Higher numbers win in cobalt; TDP and price flip.

Rig A

NVIDIA · workstation

Change

Rig B

NVIDIA · accelerator

Change

0 of 30 fields comparable

Spec	NVIDIA DGX H200	NVIDIA B200
Chip TO Chip Interconnect TB S	—	10
CPU	2x Intel Xeon Platinum 8480C	—
CPU Cores Total	112	—
Fp16 Bf16 Pflops	—	4.5
FP32 TFLOPS	—	75
FP4 Pflops Dense	—	9
FP4 Pflops Sparse	—	18
FP64 TFLOPS	—	37
FP8 Petaflops	32	—
FP8 Pflops	—	9
GPU Count	8	—
GPU Model	H200 SXM	—
HBM (GB)	—	180
Int8 Pops	—	9
Internal Storage	8x 3.84TB NVMe U.2	—
MAX Power KW	10.2	—
Memory bandwidth (TB/s)	—	8
Network MAX Gbps PER Port	400	—
Network Peak TB S	1	—
Network Ports	8x ConnectX-7 single-port (4x OSFP)	—
Nvlink Generation	—	5
Nvlink GPU TO GPU TB S	—	1.8
Nvlink PER GPU Bandwidth GB S	900	—
Nvswitch Bandwidth TB S	7.2	—
Nvswitch Count	4	—
OS Storage	2x 1.92TB NVMe M.2	—
Process Node	—	TSMC 4NP
System Memory TB	2	—
Total GPU Memory GB	1,128	—
Transistor Count Billion	—	208