Hardware
Computer hardware, from components to complete systems.
CPUs, motherboards, full servers, GPUs, and unified-memory systems — hardware for everyday computing, development, graphics, scientific workloads, and AI.
Hardware buying guide: What to buy or rent for an Ethereum full node → Compare CPU, RAM and usable NVMe requirements, configured rental prices and assumed home costs.
Current catalog
GPU and unified-memory capacity
Dedicated VRAM/HBM and shared unified memory are labeled separately. Capacity is not a performance ranking. Bars use a logarithmic scale.
Search US retailers for a consumer or workstation GPU below. Check the exact card and seller on the retailer’s site. Prices and stock are not collected here.
| Hardware | Class | Memory | Type | Qualification | Source / observed | Find retailers |
|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 4090Consumer GPU; software support and usable free VRAM depend on the system configuration. | consumer gpu | 24 GB | GDDR6X | Dedicated | Vendor ↗ | Search NeweggSearch Amazon |
| AMD Radeon RX 7900 XTXBackend and kernel support should be checked separately from capacity. | consumer gpu | 24 GB | GDDR6 | Dedicated | Vendor ↗ | Search NeweggSearch Amazon |
| NVIDIA GeForce RTX 5090Consumer GPU; advertised capacity does not guarantee runtime compatibility. | consumer gpu | 32 GB | GDDR7 | Dedicated | Vendor ↗ | Search NeweggSearch Amazon |
| AMD Radeon PRO W7900Workstation GPU with ECC support. | workstation gpu | 48 GB | GDDR6 ECC | Dedicated | Vendor ↗ | Search NeweggSearch Amazon |
| NVIDIA H100 SXMH100 NVL is a separate 94GB configuration; this row represents the 80GB SXM capacity. | datacenter accelerator | 80 GB | HBM | Dedicated | Vendor ↗ | — |
| NVIDIA H200Datacenter accelerator capacity. | datacenter accelerator | 141 GB | HBM3e | Dedicated | Vendor ↗ | — |
| AMD Instinct MI300XDatacenter accelerator capacity. | datacenter accelerator | 192 GB | HBM3 | Dedicated | Vendor ↗ | — |
| AMD Instinct MI325XDatacenter accelerator capacity. | datacenter accelerator | 256 GB | HBM3E | Dedicated | Vendor ↗ | — |
| Apple Mac Studio M3 Ultra (maximum configuration)Maximum configurable unified memory shared by CPU, GPU, and the operating system; not equivalent to dedicated VRAM. | unified memory system | 512 GB | Unified memory | Unified / shared | Vendor ↗ | — |
Related use case · Local AI
See which open weights fit.
The open-model catalog estimates Q4 and Q8 weight memory with conservative format and loading overhead, then compares Q4 estimates against capacity tiers from 8GB through 512GB.
Open the model hardware-fit matrix →