jinaai / feature-extraction Open weights updated 1 week ago

jina-embeddings-v5-omni-small

Name: jina-embeddings-v5-omni-small
Author: jinaai

Average score vs. parameter count across image (MIEB-Lite), video (MMEB-V), and audio (MAEB) benchmarks — jina-v5-omni-nano and jina-v5-omni-small define the open-weight frontier (Table 1 in the ArXiv report).

Params

1.6 B

Context

—

Downloads 30d

975 K

Likes

173

Commercial use: not allowed · cc-by-nc-4.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 28 days

1.0 M413 K

Sep 27Oct 6Oct 15Oct 24

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	3.4 GB	4.5 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: JinaEmbeddingsV5OmniModel
Parameters: 1.6 B
Tensor type: BF16
Licence: cc-by-nc-4.0
First seen on the Hub: 2026-04-01
Training datasets: undisclosed
Added to our catalog: 2026-09-27

Compare with any feature-extraction model

Popular comparisons

bge-small-en-v1.5 54.0 M bge-large-en-v1.5 9.7 M Qwen3-Embedding-0.6B 8.1 M multilingual-e5-large 6.5 M clap-htsat-unfused 946 K 1 906 K