ConfigIQ

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

Recommend sizing

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

KV cache calculator

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

GPU explorer

Compare GPUs across memory, throughput, and architecture generation.

Performance

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