Build My Rig
Mid-range

Silent Mini-ITX AI Box

Whisper-quiet AI processing for noise-sensitive environments

$1,114

7 components · 16 GB VRAM · 8 compatible models

VRAM

16 GB

TDP

300W

Noise

~28dB

Models

8

Tier

Mid-range

The Heart of This Build

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.

Buy New
AmazonBest BuyNeweggB&H Photo
Buy used: save ~$157
eBayMarketplacer/hardwareswap
Parts

7 components, $1,114 total

Estimated prices. Actual retail may vary by region. Some links may earn a small affiliate commission.

The Rest of the Build

cpu

AMD Ryzen 5 7600

6-core AM5 CPU with low power draw. The 65W TDP keeps thermals manageable in mini-ITX.

$179
Where to buy
Direct
AmazonBest BuyNeweggB&H Photo
motherboard

ASUS ROG STRIX B650E-I Gaming WiFi

Premium mini-ITX B650E board. WiFi 6E, 2.5G LAN. The best small board for AM5.

$229
Where to buy
Direct
AmazonBest BuyNeweggB&H Photo
ram

32GB DDR5-5600 (2x16GB)

32GB DDR5. Enough for AI inference and light server duties.

$79
Where to buy
Direct
AmazonBest BuyNeweggB&H Photo
storage

1TB WD Black SN850X NVMe

Fast Gen4 NVMe. 1TB for models and OS.

$79
Where to buy
Direct
AmazonBest BuyNeweggB&H Photo
psu

Corsair SF600 600W 80+ Platinum SFX

SFX form factor for mini-ITX. 600W is plenty. Platinum efficiency = less heat.

$99
Where to buy
Direct
AmazonBest BuyNeweggB&H Photo
case

Fractal Design Terra

Premium mini-ITX case with ample ventilation. Compact footprint for living room or desk.

$139
Where to buy
Direct
AmazonBest BuyNeweggB&H Photo
Runs
Compatibility

What This Build Can Run

8 AI models benchmarked on this exact hardware configuration.

Fastest Model
90tok/s

Fast

4Fast (40+ tok/s)
4Slow (<12 tok/s)
Phi-4 Mini
Q8_0
85
Llama 3.1 8B Instruct
Q8_0
55
Mistral 7B Instruct v0.3
Q5_K_M
45
Qwen 2.5 Coder 32B Instruct
Q3_K_M
10
Stable Diffusion XL 1.0
FP16
0
Whisper Large V3
FP16
0
nomic-embed-text v1.5
FP16
0
Next Step

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.

Built For

Target Use Cases

ChatCodingAI codingSelf-hosting

Want to tweak this build?

Open it in the configurator to swap components, check compatibility, and see what models you can run.

Customize This Build

Prices are estimates and may vary by retailer and region.