Skip to content
MCS · Rigs · Compare

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

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

Rig A

Cerebras Wafer-Scale Engine 3

Cerebras · accelerator

Change

Rig B

NVIDIA HGX B200

NVIDIA · accelerator

Change

0 of 24 fields comparable

⇄ swap sides
SpecCerebras Wafer-Scale Engine 3NVIDIA HGX B200
Cores900,000—
CS4 Introduced2026-08-18—
CS4 Wse3 Turbo Count3—
DIE Size MM246,225—
Fabric Bandwidth Pbit S214—
Fp16 Bf16 Pflops—36
FP32 TFLOPS—600
FP4 Pflops Dense—72
FP4 Pflops Sparse—144
FP64 TFLOPS—296
FP8 FP6 Pflops—72
Gpus—8
Int8 Pops—72
Memory Bandwidth PB S21—
Networking Bandwidth TB S—0.8
Nvlink Generation—5
Nvlink GPU TO GPU TB S—1.8
ON Chip Sram GB44—
Peak AI Petaflops125—
Process NodeTSMC 5nm—
Total HBM GB—1,400
Total Nvlink Bandwidth TB S—14.4
Transistors Trillion4—
Wse3 Turbo Peak AI Petaflops250—