Professional reliability with single-GPU CUDA
Puget Systems Datum (1x RTX 5090)
Puget Systems · Verified 2026-07-23
From $7,500
Premium pre-built with extensive testing and 3-year warranty. Good for professionals who need reliability.
Main limitation: Price premium over DIY for same GPU; 32GB VRAM limit
Some links are affiliate links. We may earn a commission at no extra cost to you. Full disclosure.
Key Specifications
| Specification | Value |
|---|---|
| Form Factor | desktop tower |
| GPU | NVIDIA GeForce RTX 5090 |
| GPU Count | 1 |
| VRAM per GPU | 32 |
| Total Accelerator Memory | 32 |
| Memory Architecture | dedicated VRAM (GDDR7) |
| GPU Memory Type | GDDR7 |
| Memory Bandwidth (per GPU) | 1792 |
| System RAM | 128 |
| RAM Type | DDR5 |
| CPU | Intel Core Ultra 9 285K or AMD Ryzen 9 9950X |
| CPU Cores | 16-24 |
| Primary Storage | 4096 |
| Storage Type | NVMe SSD |
| PCIe Generation | PCIe 5.0 |
| PCIe x16 Slots | 1-2 |
| NVLink Support | No |
| Power Supply | 1200 |
| Est. Peak Power | 850 |
| Cooling | professional air cooling |
| Dimensions | Mid-tower |
| OS | Windows 11 Pro / Ubuntu |
| Linux Support | Yes |
| Windows Support | Yes |
| WSL Support | Yes |
| CUDA Support | Yes |
| Metal Support | No |
| Warranty | 3 (Puget warranty) |
| Onsite Support | Yes (optional) |
| Release Year | 2025 |
What Models Can It Run?
Calculated estimates using weight-only memory analysis at Q4 (4-bit) quantization. Actual requirements vary by framework, context length, and runtime overhead. See methodology.
| Model | Params | Required VRAM (Q4) | Fits in 32GB? |
|---|---|---|---|
| Llama 3.1 8B | 8B | 5.52 GB | ✓ Yes |
| Llama 3.1 70B | 70B | 37.14 GB | ✗ No |
| Llama 3.2 1B | 1B | 2 GB | ✓ Yes |
| Llama 3.2 3B | 3B | 3.01 GB | ✓ Yes |
| Qwen 2.5 7B | 7B | 5.01 GB | ✓ Yes |
| Qwen 2.5 14B | 14B | 8.53 GB | ✓ Yes |
| Qwen 2.5 32B | 32B | 18.06 GB | ✓ Yes |
| Qwen 2.5 72B | 72B | 38.14 GB | ✗ No |
| Mistral 7B | 7B | 5.01 GB | ✓ Yes |
| Mixtral 8x7B | 46.7B | 25.44 GB | ✓ Yes |
| DeepSeek R1 7B | 7B | 5.01 GB | ✓ Yes |
| DeepSeek R1 32B | 32B | 18.06 GB | ✓ Yes |
| DeepSeek R1 70B | 70B | 37.14 GB | ✗ No |
| Phi-3 Medium 14B | 14B | 8.53 GB | ✓ Yes |
| Gemma 2 9B | 9B | 6.02 GB | ✓ Yes |
| Gemma 2 27B | 27B | 15.05 GB | ✓ Yes |
| Stable Diffusion XL | 6.6B | 4.81 GB | ✓ Yes |
| Flux.1 Dev | 12B | 7.52 GB | ✓ Yes |
| Flux.1 Schnell | 12B | 7.52 GB | ✓ Yes |
Max model size: 34B class models (~57B params at Q4). These are calculated estimates, not measured results.
Pros & Cons
Pros
- ✓ Linux support
- ✓ Windows support
- ✓ Onsite support available
- ✓ 3 (Puget warranty)-year warranty
Cons
- ✗ Limited accelerator memory (32GB) — 70B models require multi-GPU or offloading
- ✗ No NVLink support (multi-GPU limited to PCIe P2P)
- ✗ Price premium over DIY for same GPU; 32GB VRAM limit
Compare with Other Workstations
Apple Mac Studio M2 Ultra (192GB)
Apple Mac Studio M2 Ultra (64GB)
ArsenalPC MES2X Dual RTX 5090 AI Workstation
BIZON G3000 G2 (1x RTX 5090)
BIZON G3000 G2 (4x RTX 5090)
BOXX APEXX 8R (1x RTX PRO 6000 Blackwell)
Custom Dual RTX 4090 Training Workstation
Custom RTX 5090 AI Workstation (Value Build)
Sources & Verification
Primary source: Puget Systems Workstations
https://www.pugetsystems.com/workstations/
Verification date: 2026-07-23
Data quality: Vendor specification — from manufacturer datasheet. No hands-on testing was performed.