← All hardware
A Grace Blackwell AI supercomputer on your desk with 128GB unified memory and CUDA.
Pros
- Full CUDA ecosystem on a desktop AI box
- Strong raw compute and long-context prompt speed
- 128GB unified memory for large models
Cons
- Expensive and price rose to $4,699 on memory shortages
- Higher power draw than AMD rivals
- Inconsistent availability
✓ Where it shines / best for
- AI developers prototyping and fine-tuning large models locally
- Researchers needing data-center-class stack on the desktop
- Teams wanting to run/cluster large LLMs without cloud costs
✕ Not the best fit for
- Budget-conscious general consumers
- Gaming or general desktop productivity
- Large-scale production training (use full DGX/cloud GPUs)
Features
- ✓ On-device / offline
- ✓ Unified Memory
- ✓ Arm
- ✓ Local LLM
- ✓ Blackwell GPU
- ✓ Clustering
- ✓ CUDA
- ✓ Fine Tuning
- ✓ Petaflop
Pricing
| Plan | Price | Billing | Notes |
|---|---|---|---|
| NVIDIA DGX Spark | $3,999 | one-time | NVIDIA Founders Edition MSRP; OEM/partner versions (ASUS, Dell, HP, Lenovo, MSI) start around $2,999-$3,999 depending on storage |
| Partner editions | ~$2,999-$3,999 | one-time | Acer/ASUS/Dell/Gigabyte/HP/Lenovo/MSI variants with differing storage (1TB-4TB) |
Pricing verified from the official source. Prices change often — confirm on the vendor's site before buying.
Specifications
| cpu | Grace (Arm) |
| gpu | Blackwell die |
| power | ~300W peak |
| memory | 128GB unified LPDDR5X |
| architecture | GB10 Grace Blackwell superchip |
| ai_performance | Up to 1 petaFLOP FP4 |
Sponsored
A full review is being generated for this product and will appear here shortly.