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

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

Rig A

Google · cloud-model

Change

Rig B

NVIDIA · gpu

Change

0 of 38 fields comparable

Spec	Google Cloud TPU v5p	NVIDIA GeForce RTX 5080 Founders Edition
AI Tops	—	1,801
Bandwidth GB S	—	960
Base Clock GHZ	—	2.3
Bf16 Tflops PER Chip	459	—
Boost Clock GHZ	—	2.62
Chips PER POD	8,960	—
Cuda Cores	—	10,752
Displayport Count	—	3
Displayport Version	—	2.1b
FP8 Tflops PER Chip	459	—
HBM Bandwidth GB S	2,765	—
HBM Capacity GIB	95	—
Hdmi Count	—	1
Hdmi Version	—	2.1b
ICI Bandwidth GB S	1,200	—
Length MM	—	304
Memory BUS Bits	—	256
Memory Speed Gbps	—	30
MSRP (USD)↓ better	—	999
Pcie GEN	—	5
RT Core Tflops	—	171
RT Cores GEN	—	4
Slot Width	—	2
Sparse Cores PER Chip	4	—
Status	available (earlier generation)	—
Status Checked	—	2026-09-24
Street Price Date	—	2026-09-01
Street Price Premium PCT US	—	55
Street Price USD US Typical	—	1,550
Successor Tpu7x Chips PER POD	9,216	—
Successor Tpu7x GA	2026-03-31	—
TDP (W)↓ better	—	360
Tensor Cores GEN	—	5
Tensor Cores PER Chip	2	—
Topology	3D torus	—
VRAM (GB)	—	16
Vram Type	—	GDDR7
Width MM	—	137