JI

Jina Reranker v2 Base Multilingual

JinaGGUF by gpustackUpdated 2025-01-14
Download on Hugging Face
Parameters278M
Context1K
Layers12
Architecturebert
Smallest quant0.2 GB
Quick answer

Jina Reranker v2 Base Multilingual needs about 1.0 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 9 quants, from 0.2 GB (Q2_K) to 0.6 GB.

Jina Reranker v2 Base Multilingual – a cross‑encoder for multilingual text reranking

The Jina Reranker v2 Base Multilingual is a transformer‑based model fine‑tuned for text reranking. It accepts a query‑document pair and outputs a relevance score. The model supports up to 1024 tokens and is available in GGUF format.

Good at

  • Multilingual reranking
  • Cross‑encoder scoring
  • Long‑text handling up to 1024 tokens

Limits

  • CC‑BY‑NC‑4.0 license
  • No vision support
  • Context limited to 1024 tokens

Best for

  • Document relevance ranking
  • Search engine improvement
  • Code retrieval reranking

Who it’s for. Researchers and developers building information retrieval systems that require multilingual relevance scoring. The model is suitable for academic evaluation and prototyping.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.2 GB 0.7 GB
Fits Get file →
Q3_K0.2 GB 0.7 GB
Fits Get file →
Q4_00.2 GB 0.8 GB
Fits Get file →
Q4_K_M0.2 GB 0.8 GB
Fits Get file →
Q5_00.2 GB 0.8 GB
Fits Get file →
Q5_K_M0.2 GB 0.8 GB
Fits Get file →
Q6_K0.2 GB 0.8 GB
Fits Get file →
Q8_00.3 GB 0.8 GB
Fits Get file →
—0.6 GB 1.1 GB
Fits Get file →

For 8 GB VRAM, use Q2_K (0.2 GB file, ~1 GB memory at 8k context). For 12 GB VRAM, Q4_K_M (0.22 GB file, ~1 GB memory). For 16 GB VRAM, Q8_0 (0.31 GB file, ~1.1 GB memory). Estimates are approximate.

What GPU do you need for Jina Reranker v2 Base Multilingual?

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 the main file (0.6 GB file, about 1.4 GB in use).

Which Jina Reranker v2 Base Multilingual quant should you choose?

Q4_K_M is the usual starting point for Jina Reranker v2 Base Multilingual: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.3 GB, about 1.4 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 0.2 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

Architecturebert
Parameters278M
Layers12
Trained context1,024 tokens
KV cache (fp16)36 KB per token

Source

Quantized bygpustack
FamilyJina
Downloads (HF)1,781
Last updated2025-01-14

Frequently asked questions about Jina Reranker v2 Base Multilingual

How much VRAM does Jina Reranker v2 Base Multilingual need?

About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.2 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 Reranker v2 Base Multilingual on an 8 GB GPU?

Yes, with the smaller files: the 0.6 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Jina Reranker v2 Base Multilingual GGUF?

It depends on the quant: Q2_K is 0.2 GB, Q3_K is 0.2 GB, Q4_0 is 0.2 GB, Q4_K_M is 0.2 GB, Q5_0 is 0.2 GB, Q5_K_M is 0.2 GB and 3 more.

What context length does Jina Reranker v2 Base Multilingual support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 1K.

Where can I download Jina Reranker v2 Base Multilingual GGUF?

The files are on Hugging Face in the gpustack/jina-reranker-v2-base-multilingual-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 Reranker v2 Base Multilingual use?

Hugging Face lists the license as cc-by-nc-4.0. 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, the Q2_K quantization requires about 1 GB memory at 8k context, fitting within 8 GB VRAM.

Is this model suitable for commercial use?

No, the CC‑BY‑NC‑4.0 license restricts commercial deployment. Contact Jina AI for commercial options.

How do I load the GGUF file with llama.cpp?

Use llama.cpp with the --model flag pointing to the chosen quant file, e.g., --model jina-reranker-v2-base-multilingual.Q2_K.gguf.

Similar models

Browse all →

More from gpustack

All by gpustack →

More Jina models

All Jina →

Other tiny models

All tiny models →