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

NVIDIA H200

NVIDIA · accelerator

Change

Rig B

AWS Trainium2

AWS · cloud-model

Change

0 of 34 fields comparable

⇄ swap sides
SpecNVIDIA H200AWS Trainium2
BF16 TFLOPS (sparse)1,979—
Bf16 Tflops PER Chip—667
Chips PER Trn2 Instance—16
Chips PER Ultraserver—64
Form factorSXM—
FP16 TFLOPS (sparse)1,979—
FP32 TFLOPS67—
FP64 TFLOPS34—
FP8 Dense Petaflops PER Chip—1.3
FP8 Sparse Petaflops PER Chip—5.2
FP8 TFLOPS (sparse)3,958—
HBM (GB)141—
HBM Bandwidth TB S PER Chip—2.9
HBM Capacity GB PER Chip—96
HBM Type—HBM3
INT8 TOPS (sparse)3,958—
Memory bandwidth (TB/s)4.8—
Memory typeHBM3e—
MIG Instances7—
MIG PER Instance GB18—
Neuroncores PER Chip—8
NVLink bandwidth (GB/s)900—
Pcie Gen5 Bandwidth GB S128—
TDP max (W)↓ better700—
Trainium3 GA—2025-12-02
Trainium3 HBM Bandwidth TB S—4.9
Trainium3 Hbm3e GB PER Chip—144
Trn2 Instance FP8 Petaflops—20.8
Trn2 Instance HBM TB—1.5
Trn3 Ultraserver FP8 Pflops—362
Trn3 Ultraserver MAX Chips—144
Ultraserver FP8 Petaflops—83.2
Ultraserver Total HBM Bandwidth TB S—185
Ultraserver Total HBM TB—6