JI

jina embeddings v2 base de

JinaGGUF by second-stateUpdated 2024-12-11
Download on Hugging Face
Parameters160M
Context8K
Layers12
Architecturejina-bert-v2
Smallest quant0.1 GB
Quick answer

jina embeddings v2 base de needs about 0.9 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 0.1 GB (Q2_K) to 0.3 GB (F16).

German/English bilingual text embedding model

jina-embeddings‑v2‑base‑de is a 161 million parameter BERT‑style model for German and English. It supports up to 8192 tokens and is optimized for mono‑lingual and cross‑lingual embedding tasks.

Good at

  • German‑English cross‑lingual embeddings
  • High‑quality sentence embeddings
  • Efficient mean‑pooling integration

Limits

  • No vision support
  • Requires 8192 context length
  • Apache‑2.0 license

Best for

  • Embedding search engines
  • Cross‑lingual semantic similarity
  • Code‑to‑text embedding tasks

Who it’s for. Developers building bilingual search or recommendation systems that need German and English embeddings. Researchers needing a lightweight, open‑source model for cross‑lingual experiments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.9 GB
Fits Get file →
Q3_K_S0.1 GB 0.9 GB
Fits Get file →
Q3_K_M0.1 GB 0.9 GB
Fits Get file →
Q3_K_L0.1 GB 0.9 GB
Fits Get file →
Q4_00.1 GB 0.9 GB
Fits Get file →
Q4_K_S0.1 GB 0.9 GB
Fits Get file →
Q4_K_M0.1 GB 0.9 GB
Fits Get file →
Q5_00.1 GB 0.9 GB
Fits Get file →
Q5_K_S0.1 GB 0.9 GB
Fits Get file →
Q5_K_M0.1 GB 0.9 GB
Fits Get file →
Q6_K0.1 GB 0.9 GB
Fits Get file →
Q8_00.2 GB 1.0 GB
Fits Get file →
F160.3 GB 1.1 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.11 GB) or Q5_K_M (0.12 GB). For 4 GB VRAM, Q3_K_S (0.09 GB) or Q4_0 (0.1 GB) are suitable. Higher precision Q8_0 (0.17 GB) or F16 (0.32 GB) requires more memory but offers full precision.

What GPU do you need for jina embeddings v2 base de?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F16 (0.3 GB file, about 1.1 GB in use).

Which jina embeddings v2 base de quant should you choose?

Q4_K_M is the usual starting point for jina embeddings v2 base de: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.2 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 0.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturejina-bert-v2
Parameters160M
Layers12
Trained context8,192 tokens
KV cache (fp16)36 KB per token

Source

Quantized bysecond-state
FamilyJina
Licenseapache-2.0
Downloads (HF)1,092
Last updated2024-12-11

Frequently asked questions about jina embeddings v2 base de

How much VRAM does jina embeddings v2 base de need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run jina embeddings v2 base de on an 8 GB GPU?

Yes, with F16: the 0.3 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of jina embeddings v2 base de GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, Q4_0 is 0.1 GB, Q4_K_S is 0.1 GB and 7 more.

What context length does jina embeddings v2 base de support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.3 GB at 8K.

Where can I download jina embeddings v2 base de GGUF?

The files are on Hugging Face in the second-state/jina-embeddings-v2-base-de-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does jina embeddings v2 base de use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, use Q4_K_M or Q5_K_M quantizations, which fit within 8 GB VRAM.

Does this model support image inputs?

No, it is a text‑only embedding model.

What context length does it support?

It supports up to 8192 tokens.

Other GGUFs of jina-embeddings-v2-base-de

Similar models

Browse all →

More from second-state

All by second-state →

More Jina models

All Jina →

Other tiny models

All tiny models →