Mid-Range
Mid-RangeHome AI Server
Silent Mini-ITX AI Box
$1,253
16 GB VRAM300W TDP~28dB7 components
Inside This Build
Components
| Category | Component | Price | Rationale | Buy |
|---|---|---|---|---|
| gpu |  NVIDIA GeForce RTX 4060 Ti 16GB | $449 | 16GB VRAM in a compact 240mm card. Low 165W TDP means less heat and noise in a small case. | |
| cpu |  AMD Ryzen 5 7600 | $179 | 6-core AM5 CPU with low power draw. The 65W TDP keeps thermals manageable in mini-ITX. | |
| motherboard |  ASUS ROG STRIX B650E-I Gaming WiFi | $229 | Premium mini-ITX B650E board. WiFi 6E, 2.5G LAN. The best small board for AM5. | |
| ram | 32GB DDR5-5600 (2x16GB) | $79 | 32GB DDR5. Enough for AI inference and light server duties. | |
| storage | WD1TB WD Black SN850X NVMe | $79 | Fast Gen4 NVMe. 1TB for models and OS. | |
| psu |  Corsair SF600 600W 80+ Platinum SFX | $99 | SFX form factor for mini-ITX. 600W is plenty. Platinum efficiency = less heat. | |
| case | Fractal DesignFractal Design Terra | $139 | Premium mini-ITX case with excellent ventilation. Compact footprint for living room or desk. | |
| Total | $1,253 | |||
Shop Components
Search links — prices and availability vary by retailer.
Buy Used GPU
Prices and availability vary. Inspect hardware before purchasing.
What This Runs
AI models tested on this build's hardware.
| Model | Quant | Speed |
|---|---|---|
| Llama 3.1 8B Instruct | Q8_0 | 55 tok/s |
| Llama 3.2 3B Instruct | Q8_0 | 90 tok/s |
| Phi-4 Mini | Q8_0 | 85 tok/s |
| Qwen 2.5 Coder 32B Instruct | Q3_K_M | 10 tok/s |
| Mistral 7B Instruct v0.3 | Q5_K_M | 45 tok/s |
| Stable Diffusion XL 1.0 | FP16 | — |
| Whisper Large V3 | FP16 | — |
| nomic-embed-text v1.5 | FP16 | — |
Upgrade Path
The mini-ITX form factor limits upgrades. The biggest improvement would be swapping to an RTX 4070 Ti Super (fits at 285mm in some configs) for 16GB VRAM with more bandwidth. Check case clearance first.
Target Use Cases
ChatCodingAI CodingSelf-Hosting
Last updated: 2026-03-15.