gpu sizing
3 articles
Self Hosted Transcription vs API Cost at Equal Quality
Compare self hosted transcription vs API cost in 2026 with channel-aware billing, L4 and L40S rental inputs, quality acceptance tests, outage reserve, and a separate deadline-based batch worksheet.
November 1, 2026• 24 min read
self hosted transcription vs api costprivate transcription costfaster whisper
KV Cache Memory Calculator: Context, Concurrency and GPUs
A 2026 guide to architecture-aware KV cache sizing: calculate bytes per token, replay prompt/output distributions, reconcile vLLM and TensorRT-LLM capacity, and validate replica count against latency targets.
October 12, 2026• 24 min read
kv cache memory calculatorkv cache size calculatorkv cache memory formula
LLM Training Memory Calculator for ZeRO and FSDP
A 2026 planning model for per-rank LLM training memory, ZeRO and FSDP sharding, GPU count, CPU or NVMe offload, topology rounding, and measured validation.
September 18, 2026• 21 min read
llm training memory calculatorzero memory calculatorfsdp memory calculator