Compare
Side by side, in plain words
Pick up to three machines or cards to see how they stack up.
Swipe the table sideways to see every column.
![]() | ![]() | ||
|---|---|---|---|
| Price | $4,699 – $10,593 | $4,790 | |
| Memory | 128 GB unified | 128 GB unified | |
| AI models (approx.) | Up to 120B+ at 4-bit, 70B at 8-bit | Up to 120B+ at 4-bit, 70B at 8-bit | |
| Superchip | NVIDIA GB10 Grace Blackwell | — | |
| CPU | 20-core Arm (10 × Cortex-X925, 10 × Cortex-A725) | — | |
| GPU | NVIDIA Blackwell, 5th-generation Tensor Cores | — | |
| AI performance | Up to 1 petaFLOP FP4 (with sparsity) | — | |
| Memory | 128 GB LPDDR5x coherent unified memory, 273 GB/s | 128 GB LPDDR5X-8000 unified memory (soldered) | |
| Storage | 4 TB NVMe (NVIDIA Founders Edition; partner versions vary) | 2 × M.2 2280 PCIe 4.0 slots | |
| Networking | NVIDIA ConnectX-7 (200 Gb/s) and 10 Gigabit Ethernet | 2 × 10 Gigabit Ethernet | |
| Ports | 4 × USB Type-C, 1 × HDMI 2.1a | — | |
| Operating system | NVIDIA DGX OS (Ubuntu-based) | — | |
| Size | 150 × 150 × 50.5 mm | — | |
| Processor | — | AMD Ryzen AI Max+ 395 | |
| CPU cores | — | 16 cores / 32 threads (Zen 5), up to 5.1 GHz | |
| Graphics | — | AMD Radeon 8060S integrated, 40 RDNA 3.5 compute units | |
| NPU | — | AMD XDNA 2, up to 50 TOPS | |
| USB4 | — | 2 ports | |
| Wireless | — | Wi-Fi 7 | |
| Best for | Developers who prototype, fine-tune and test models on CUDA before moving them to bigger hardware. | Anyone who wants to run 70B-class models at home in a small, quiet box without building a multi-GPU tower. | |
| View details → | View details → |
Not sure how much memory you need? Check which machine runs which model.

