Side-by-side, with the numbers that matter.
Two rigs, one table. Higher numbers win in cobalt; TDP and price flip.
Rig A
Boston Dynamics Atlas
Boston Dynamics · edge
Change
- 1X Neo
- Agility Robotics Digit
- Alibaba Qwen2.5-72B-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
- 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
- SambaNova SN40L Reconfigurable Dataflow Unit
- Sanctuary AI Phoenix
- Tesla Optimus
- The Stargate Project
- Unitree B2
- Unitree G1
- Unitree H1
Rig B
NVIDIA GeForce RTX 4090 Founders Edition
NVIDIA · gpu
Change
- 1X Neo
- Agility Robotics Digit
- Alibaba Qwen2.5-72B-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
- 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
- SambaNova SN40L Reconfigurable Dataflow Unit
- Sanctuary AI Phoenix
- Tesla Optimus
- The Stargate Project
- Unitree B2
- Unitree G1
- Unitree H1
0 of 30 fields comparable
⇄ swap sides| Spec | Boston Dynamics Atlas | NVIDIA GeForce RTX 4090 Founders Edition |
|---|---|---|
| AI Partner | Google DeepMind foundation models | — |
| Bandwidth GB S | — | 1,008 |
| Battery Life Hours | 4 | — |
| Budget Ceiling USD | — | 2,000 |
| Compute Capability Digits | — | 89 |
| Deployment Status | pilot — fleets committed for 2026 to Hyundai RMAC and Google DeepMind | — |
| DOF | 56 | — |
| Height M | 1.9 | — |
| Hyundai Planned Atlas Units | 25,000 | — |
| IP Rating | IP67 | — |
| Manufacturing Partner | Hyundai Motor Group / Hyundai Mobis actuators | — |
| MSRP (USD)↓ better | — | 1,599 |
| Operating Temp High C | 40 | — |
| Operating Temp LOW C | -20 | — |
| Product Unveiling Event | CES Las Vegas (January 5, 2026) | — |
| Product Unveiling Year | 2,026 | — |
| Production END Reported | — | 2024-10 |
| Reach M | 2.3 | — |
| Rmac Opened | 2026-09-21 | — |
| RTX 4090 Model | — | 4,090 |
| RTX 5090 Model | — | 5,090 |
| Simulation Partner | NVIDIA | — |
| Status | — | discontinued (no longer sold new by NVIDIA) |
| Status Checked | 2026-09-24 | 2026-09-24 |
| TDP (W)↓ better | — | 450 |
| US Robot Factory Capacity PER Year | 30,000 | — |
| VRAM (GB) | — | 24 |
| Weight Capacity Instant KG | 50 | — |
| Weight Capacity Sustained KG | 30 | — |
| Weight KG | 90 | — |