jinaai / feature-extraction updated 3 months ago

jina-clip-v2

This model is based on the paper jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images.

Params
870 M
Context
Downloads 30d
530 K
Likes
341
Commercial use: not allowed · cc-by-nc-4.0 Not gated SAFETENSORS 94 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days
614 K530 K
Jul 28Jul 31Aug 3Aug 6

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors f16 1.7 GB 2.5 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
JinaCLIPModel
Parameters
870 M
Tensor type
F16
Licence
cc-by-nc-4.0
First seen on the Hub
2024-10-08
Training datasets
undisclosed
Added to our catalog
2026-07-28