AI & ML interests
Open-model inference APIs, OpenAI-compatible endpoints, LLM · vision · speech · video, RTX PRO 6000 GPU Cloud
Recent Activity
Articles
Language and vision models on EcoHash, with our own TTFT, per-token latency and precision published next to every number.
Text-to-image on EcoHash from $0.01 an image. Latency and images per minute measured end-to-end on one RTX PRO 6000.
Language and vision models on EcoHash, with our own TTFT, per-token latency and precision published next to every number.
Speech recognition and synthesis on EcoHash. WER, real-time factor and time to first audio, all measured by us end-to-end.
Text-to-image on EcoHash from $0.01 an image. Latency and images per minute measured end-to-end on one RTX PRO 6000.
Embedding and reranking on EcoHash - the two halves of a RAG pipeline, with the measured cost of each stage.