Side-by-side, with the numbers that matter.
Two rigs, one table. Higher numbers win in cobalt; TDP and price flip.
Rig A

AWS Trainium2
AWS · cloud-model
Change
- 1X Neo
- Agility Robotics Digit
- Alibaba Qwen3-72B-Instruct (Q4 quant)
- AMD Instinct MI300X
- AMD Instinct MI325X
- AMD Instinct MI355X
- Anthropic Claude Opus 4.7
- Apple Mac Pro (M2 Ultra, 2023)
- Apple Mac Studio (M3 Ultra)
- Apple MacBook Pro 16-inch, M4 Max (2024)
- Apptronik Apollo
- Aurora
- AWS Trainium2
- Boston Dynamics Atlas
- Boston Dynamics Spot
- Cerebras Wafer-Scale Engine 3
- El Capitan
- Figure 02
- Frontier (OLCF-5)
- Google Cloud TPU v5p
- Groq Language Processing Unit
- Intel Gaudi 3 HL-325L
- MSI GeForce RTX 5090 Suprim Liquid
- NVIDIA B100
- NVIDIA B200
- NVIDIA DGX B200
- NVIDIA DGX H200
- NVIDIA DGX Spark
- NVIDIA Eos DGX SuperPOD
- NVIDIA GB200
- NVIDIA GB200 NVL72
- NVIDIA GeForce RTX 4090 Founders Edition
- NVIDIA GeForce RTX 5070 Ti Founders Edition
- NVIDIA GeForce RTX 5080 Founders Edition
- NVIDIA GeForce RTX 5090 Founders Edition
- NVIDIA GH200 Grace Hopper
- NVIDIA H100
- NVIDIA H200
- NVIDIA HGX B200
- NVIDIA Jetson AGX Thor
- NVIDIA RTX PRO 4500 Blackwell
- NVIDIA RTX PRO 5000 Blackwell
- NVIDIA RTX PRO 6000 Blackwell
- OpenAI GPT-5 Core
- SambaNova SN40L Reconfigurable Dataflow Unit
- Sanctuary AI Phoenix
- Tesla Optimus
- The Stargate Project
- Unitree B2
- Unitree G1
- Unitree H1
Rig B

Intel Gaudi 3 HL-325L
Intel · accelerator
Change
- 1X Neo
- Agility Robotics Digit
- Alibaba Qwen3-72B-Instruct (Q4 quant)
- AMD Instinct MI300X
- AMD Instinct MI325X
- AMD Instinct MI355X
- Anthropic Claude Opus 4.7
- Apple Mac Pro (M2 Ultra, 2023)
- Apple Mac Studio (M3 Ultra)
- Apple MacBook Pro 16-inch, M4 Max (2024)
- Apptronik Apollo
- Aurora
- AWS Trainium2
- Boston Dynamics Atlas
- Boston Dynamics Spot
- Cerebras Wafer-Scale Engine 3
- El Capitan
- Figure 02
- Frontier (OLCF-5)
- Google Cloud TPU v5p
- Groq Language Processing Unit
- Intel Gaudi 3 HL-325L
- MSI GeForce RTX 5090 Suprim Liquid
- NVIDIA B100
- NVIDIA B200
- NVIDIA DGX B200
- NVIDIA DGX H200
- NVIDIA DGX Spark
- NVIDIA Eos DGX SuperPOD
- NVIDIA GB200
- NVIDIA GB200 NVL72
- NVIDIA GeForce RTX 4090 Founders Edition
- NVIDIA GeForce RTX 5070 Ti Founders Edition
- NVIDIA GeForce RTX 5080 Founders Edition
- NVIDIA GeForce RTX 5090 Founders Edition
- NVIDIA GH200 Grace Hopper
- NVIDIA H100
- NVIDIA H200
- NVIDIA HGX B200
- NVIDIA Jetson AGX Thor
- NVIDIA RTX PRO 4500 Blackwell
- NVIDIA RTX PRO 5000 Blackwell
- NVIDIA RTX PRO 6000 Blackwell
- OpenAI GPT-5 Core
- SambaNova SN40L Reconfigurable Dataflow Unit
- Sanctuary AI Phoenix
- Tesla Optimus
- The Stargate Project
- Unitree B2
- Unitree G1
- Unitree H1
0 of 25 fields comparable
⇄ swap sides| Spec | AWS Trainium2 | Intel Gaudi 3 HL-325L |
|---|---|---|
| Bf16 Tflops | — | 1,835 |
| Bf16 Tflops PER Chip | 667 | — |
| Chips PER Trn2 Instance | 16 | — |
| Chips PER Ultraserver | 64 | — |
| Ethernet Port Gbps | — | 200 |
| Ethernet Ports | — | 24 |
| Form factor | — | OAM |
| FP8 Dense Petaflops PER Chip | 1.3 | — |
| FP8 Sparse Petaflops PER Chip | 5.2 | — |
| FP8 Tflops | — | 1,835 |
| HBM (GB) | — | 128 |
| HBM Bandwidth TB S PER Chip | 2.9 | — |
| HBM Type | — | HBM2E |
| Hbm3e Capacity GB PER Chip | 96 | — |
| Memory bandwidth (TB/s) | — | 3.7 |
| MME Engines | — | 8 |
| Neuroncores PER Chip | 8 | — |
| Process Node NM | — | 5 |
| Sram MB | — | 96 |
| TDP (W)↓ better | — | 900 |
| TPC Engines | — | 64 |
| Trn2 Instance FP8 Petaflops | 20.8 | — |
| Ultraserver FP8 Petaflops | 83.2 | — |
| Ultraserver Total HBM Bandwidth TB S | 185 | — |
| Ultraserver Total HBM TB | 6 | — |