Model reference · open weights
jina-embeddings-text-small is an open-weight embedding model from jinaai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
jina-embeddings-v5-text-small jina-embeddings-v5-text-small is the fifth generation of Jina AI's multilingual embedding models, released on February 18, 2026. For a lighter alternative, see jina-embeddings-v5-text-nano (239M parameters). Elastic Inference Service | ArXiv | Release Note | Blog Model Overview jina-embeddings-v5-text-small scores 71.7 average on MTEB English v2 and 67.7 on MMTEB with 677M parameters, the highest among multilingual embedding models under 1B parameters. Built on Qwen3-0.6B-Base and trained by combining embedding distillation from Qwen3-Embedding-4B with task-specific contrastive losses, it supports 119+ languages with up to 32K tokens and produces embeddings robust under truncation and binary quantization. It is part of the jina-embeddings-v5-text model family, which also includes jina-embeddings-v5-text-nano, a smaller model for resource-constrained use cases. Training and Evaluation For training details and evaluation results, see our technical report. Usage The following Python packages are required: - transformers=4.57.0 - torch=2.8.0 - peft=0.15.2 Optional / Recommended - flash-attention: Installing flash-attention is recommended for improved inference speed and efficiency, but not mandatory. - sentence-transformers: If you want to use the model via the sentence-transformers interface, install this package as well. The fastest way to use v5-text in production. Elastic Inference Service (EIS) provides managed embedding inference with built-in scaling, so you can generate embeddings directly within your Elastic deployment. See the Elastic Inference Service documentation for setup details. We provide separate model versions for each task (retrieval, text-matching, classification, clustering). For each model, the task-specific adapter is merged into the base model weights. This modification enables simpler compatibility with vLLM. Instructions and usage examples for each task are available in their respective model repositories: - jina-embeddings-v5-text-small-retrieval - jina-embeddings-v5-text-small-text-matching - jina-embeddings-v5-text-small-classification - jina-embeddings-v5-text-small-clustering We provide separate model ver
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | jinaai |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 596M |
| Context | 32k tokens |
| Variants | 1 |
| Runs with | transformers |
| Based on | Qwen/Qwen3-0.6B-Base |
| Released | 2026-01-22 |
| Popularity | 196k downloads / month |
| Likes | 198 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| jina-embeddings-v5-text-small | 596M | BF16 | ~1.4 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys jina-embeddings-text-small for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (jina-embeddings-text-small below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"jina-embeddings-text-small","input":"text to embed"}'
Licence
The weights are open but cc-by-nc-4.0 needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗
Explore