Elastic Looks to Speed Up Jina Model Inference by 8x Using NVIDIA RTX GPUs
Elastic, Wednesday, October 21st, 2026
Elastic is moving Jina API and Elastic Inference Service models to NVIDIA RTX Pro 6000 Blackwell GPUs for faster inference.
Elastic says it is moving its Jina AI models from NVIDIA L40 GPUs to NVIDIA RTX Pro 6000 Blackwell Server Edition GPUs.
Jina provides reader, OCR, embedding and reranking models offered through the Jina API and Elastic Inference Service.
Some Jina API models already run on the new GPUs, and customers get the speedup without changes.
Elastic reports promising early results and is aiming for up to 8x faster inference for agentic AI workloads.