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

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

Rig A

AWS · cloud-model

Change

Rig B

1X Technologies · edge

Change

0 of 46 fields comparable

Spec	AWS Trainium2	1X Neo
AI Compute FP4 Tflops	—	2,070
ARM DOF	—	7
ARM Payload KG	—	8
Battery Runtime Hours	—	4
Battery WH	—	842
Bf16 Tflops PER Chip	667	—
Canonical Name	—	1X Neo
Carry Capacity KG	—	25
Charge Minutes PER Hour Runtime	—	6
Chips PER Trn2 Instance	16	—
Chips PER Ultraserver	64	—
Compute Chipset	—	1X NEO Cortex (NVIDIA Jetson Thor)
Deployment Status	—	preorder
Deposit USD	—	200
First Delivery Year	—	2,026
Form factor	—	humanoid
FP8 Dense Petaflops PER Chip	1.3	—
FP8 Sparse Petaflops PER Chip	5.2	—
Hand DOF	—	22
HBM Bandwidth TB S PER Chip	2.9	—
HBM Capacity GB PER Chip	96	—
HBM Type	HBM3	—
Height CM	—	168
LEG DOF	—	6
Lift Capacity KG	—	70
Neck DOF	—	3
Neuroncores PER Chip	8	—
Preorder Price USD	—	20,000
RUN Speed MPS	—	6.2
Spine DOF	—	2
Status Checked	—	2026-09-24
Subscription USD Month	—	499
Total DOF	—	80
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	—
Vendor	—	1X Technologies
Walking Speed MPS	—	1.4
Weight KG	—	30