AI Data Center Power, Cooling and Water Calculator
Wired White v1 Estimate AI rack power, grid draw, cooling duty and water use. Compare wet towers, air-cooled chillers and dry cooling with PUE, WUE and annual totals.
AI and computing
Hardware sizing for AI: how much GPU memory and speed a language model needs for its size, quantization and context length.
Wired White v1 
PC and AI Rig Power Supply Calculator | PSU Sizing
Wired White v1 Size a PC or multi-GPU AI rig PSU from wattages, check ATX 3.1 transients, estimate wall power and yearly cost, and explore 12V-2x6 contact heating.
Orbital AI Data Center: Solar and Radiator Sizing
Wired White v1 Size solar arrays, eclipse batteries and radiators for an orbital AI data center. Compare temperature, orbit geometry, launch mass and launch-price assumptions.
LLM VRAM and Throughput Calculator
Wired White v1 Find which local LLMs fit your GPU, Mac or CPU—or which hardware fits a model. Compare KV memory, prefill, decode, runtime support and measured speed references.
LLM Serving Capacity: KV Cache, Concurrent Users and Queue
Wired White v1 Estimate KV cache capacity, concurrent requests, queue delay and streaming latency. Compare parallel agent completion and cost against local server and API limits.
Fine-Tuning VRAM and Time Calculator: Full, LoRA and QLoRA
Wired White v1 Estimate inference and training VRAM, maximum sequence length and microbatch, runtime and cost for full fine-tuning, LoRA and QLoRA. Compare GPU sharding, checkpointing and editable MFU assumptions.
AI Agent Cost Calculator: per Run, Month and Successful Task
Wired White v1 Estimate AI agent costs with growing history, cache expiry, mixed models, retries and human review. See cost per run, per month and per successful task.
Multi-GPU LLM Calculator: VRAM Split and RAM Offload
Wired White v1 Compare 2×3090, RTX 5090 and Apple silicon. Plan layers, tensor parallelism or MoE experts in RAM, with per-device memory, prefill/decode estimates and cited benchmarks.
Local LLM vs API vs Rented GPU: Cost and Break-Even
Wired White v1 Compare owning an AI rig, renting a GPU and using an API. Include prefill, decode, idle power, resale, upkeep, caching and reasoning tokens to find cost per million tokens and break-even.
