FiveTech Support Forums

🔌 Realistic Power-Consumption Estimate for Your AI Server

(Ryzen 9 7950X + RTX 3090 + 64 GB RAM + SSD)

1) Idle Power Consumption (no real load)
Component Power
Ryzen 9 7950X _30–45 W
RTX 3090 idle _25–35 W
Mainboard, RAM, SSD _20–35 W
Total _80–120 W

➡️ Realistic idle average: ₁₀₀ W
(The RTX 3090 is quite efficient when the monitor sleeps.)

2) Real AI Inference Load (70–80% GPU load)

RTX 3090 inference: 250–320 W

Ryzen 9 7950X moderate load: 40–90 W

Other system components: 30–50 W

➡️ Total under normal AI load: _320–450 W

This corresponds to real usage such as:

Running 1–3 models simultaneously

Hotel queries, DMS OCR, microservices

Web server + backend logic on CPU

3) Maximum Load (GPU 100% + CPU 100%)

This rarely happens in daily use — only during:

Training / fine-tuning

Heavy benchmarking

Multiple pipelines running at full load

Component Power
RTX 3090 320–360 W
Ryzen 9 7950X 120–170 W
Other 40–50 W

➡️ Peak total: _480–580 W

💶 Monthly Power Cost (example)

Assuming 350 W average, 24/7 operation:

0.35 kW × 24 h × 30 days = 252 kWh/month
252 kWh × 0.25 €/kWh ≈ 63 € per month

💡 But in typical hotel microservice workloads:

7B–13B models

Batch size 1–4

Sporadic client queries

No continuous full load

➡️ Realistic daily average: _200–260 W

Which results in:

➡️ _35–50 € per month (24/7)

📌 Summary
Realistic consumption (24/7 AI server):

Idle: ₁₀₀ W

Normal AI load: ₃₅₀ W

Peak: ₅₅₀ W

Monthly cost: 35–65 €, depending on workload.