Side-by-side, with the numbers that matter.
Two rigs, one table. Higher numbers win in cobalt; TDP and price flip.
Rig A
Unitree B2
Unitree Robotics · 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
Google Cloud TPU v5p
Google · cloud-model
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 51 fields comparable
⇄ swap sides| Spec | Unitree B2 | Google Cloud TPU v5p |
|---|---|---|
| Battery AH | 45 | — |
| Battery Voltage V | 58 | — |
| Battery WH | 2,250 | — |
| Bf16 Tflops PER Chip | — | 459 |
| Canonical Name | Unitree B2 | — |
| Chips PER POD | — | 8,960 |
| Commercial Release Year | 2,024 | — |
| Compute Modules MAX | 3 | — |
| Compute Optional CPU | Intel Core i7 | — |
| Compute Optional GPU | NVIDIA Jetson Orin NX | — |
| Compute Standard | Intel Core i5 | — |
| Deployment Status | commercial | — |
| Depth Cameras | 2 | — |
| Form factor | quadruped | — |
| FP8 Tflops PER Chip | — | 459 |
| HBM Bandwidth GB S | — | 2,765 |
| HBM Capacity GIB | — | 95 |
| ICI Bandwidth GB S | — | 1,200 |
| IP Rating | IP67 | — |
| Lidars | 1 | — |
| Loaded Weight KG | 20 | — |
| MAX Slope Degrees | 45 | — |
| MAX Speed M S | 6 | — |
| MAX Stair Height CM | 40 | — |
| MSRP (USD)↓ better | 100,000 | — |
| Operating Temp MAX C | 55 | — |
| Operating Temp MIN C | -20 | — |
| Operating Temp MIN C ABS | 20 | — |
| Optical Cameras | 2 | — |
| Payload Standing KG | 120 | — |
| Payload Walking KG | 40 | — |
| Prone Height MM | 330 | — |
| Prone Length MM | 880 | — |
| Prone Width MM | 460 | — |
| Range Loaded KM | 15 | — |
| Range Unloaded KM | 20 | — |
| Runtime Loaded Hours | 4 | — |
| Runtime Unloaded Hours | 5 | — |
| Sparse Cores PER Chip | — | 4 |
| Standing Height MM | 645 | — |
| Standing Length MM | 1,098 | — |
| Standing Width MM | 450 | — |
| Status | — | available (earlier generation) |
| Status Checked | 2026-09-24 | — |
| Store Available | false | — |
| Successor Tpu7x Chips PER POD | — | 9,216 |
| Successor Tpu7x GA | — | 2026-03-31 |
| Tensor Cores PER Chip | — | 2 |
| Topology | — | 3D torus |
| Vendor | Unitree Robotics | — |
| Weight KG | 60 | — |