ConfigIQ

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

A free community service, provided as-is without warranty. All results are best-effort estimates for planning, not guarantees of real-world performance.

Recommend sizing

Find the optimal GPU configuration for a workload target using the AISimulators engine.

Open tool →

KV cache calculator

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

Open tool →

GPU explorer

Compare GPUs across memory, throughput, and architecture generation.

Open tool →

Performance

Estimate TTFT, TPOT, and throughput for your model and parallelism configuration.

Open tool →