Run jina-embeddings-v5-text-nano

The fastest way to get this model running locally is via Docker.

Make sure to follow the instructions below.

The loader auto-caches the model archive (several GBs included).

Once launched, the setup wizard will detect your specs to configure the model for maximum efficiency.

🛠 Hash code: 6a368833dee1f54ed3fd90f74d3d3b64 — Last modification: 2026-06-25



  • Processor: high single-core performance needed for token latency
  • RAM: required: 16 GB absolute minimum for small models
  • Disk Space: at least 100 GB for multiple local LLM variants
  • GPU: modern architecture (Ada Lovelace / Ampere minimum)

The jina-embeddings-v5-text-nano model delivers compact yet high‑quality text embeddings optimized for edge devices. With only 2 million parameters, it achieves competitive performance on semantic similarity tasks while maintaining a small memory footprint. Its inference latency is under 5 ms on typical CPUs, making it ideal for real‑time applications that require fast processing. The model supports multiple languages and preserves contextual nuances better than earlier nano‑sized alternatives. Key metrics are summarized in the following table:

Parameters2 million
Size (MB)7.8
Latency (ms)<5
Throughput (tokens/s)2000
Supported Languages30

Leave a Reply

Your email address will not be published. Required fields are marked *