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.
#KV cache
Wired White v1 
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.
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.
