Work in progress

GPU Calc

LLM inference sizing, GPU comparison, and cost modeling for engineers and infrastructure teams.

KV Cache Calculator

Calculate KV cache memory requirements for any model on supported GPU systems.

Advanced Calculator

Detailed inference sizing with batching, quantization, KV cache, and cost modeling.

GPU Explorer

Compare GPUs across memory, throughput, cost, and availability tiers.

Hybrid Savings

Model cost savings between cloud, on-premise, and hybrid GPU deployment strategies.

Routing Economics

Analyze request routing between model tiers to optimize cost vs quality tradeoffs.