JI

jina reranker v1 tiny en

JinaGGUF by gpustackUpdated 2025-01-15
Download on Hugging Face
Parameters33M
Context8K
Layers4
Architecturejina-bert-v2
Smallest quant0.0 GB
Quick answer

jina reranker v1 tiny en needs about 0.6 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 9 quants, from 0.0 GB (Q2_K) to 0.1 GB.

Fast, small reranker for text similarity

jina reranker v1 tiny en is a 33.0 million parameter model built on JinaBERT. It supports up to 8,192 tokens and is optimized for quick inference. The model is available in several GGUF quantizations.

Good at

  • Fast reranking
  • Short‑token embeddings
  • Low‑memory inference

Limits

  • No vision support
  • Limited to 8,192 tokens
  • Apache‑2.0 license

Best for

  • Search engine ranking
  • Document similarity filtering
  • Quick relevance scoring

Who it’s for. Developers needing a lightweight reranker for text search or recommendation systems. The model is suitable for edge deployments or environments with limited GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.0 GB 0.6 GB
Fits Get file →
Q4_00.0 GB 0.6 GB
Fits Get file →
Q3_K_M0.0 GB 0.6 GB
Fits Get file →
Q5_00.0 GB 0.6 GB
Fits Get file →
Q4_K_M0.0 GB 0.6 GB
Fits Get file →
Q5_K_M0.0 GB 0.6 GB
Fits Get file →
Q6_K0.0 GB 0.6 GB
Fits Get file →
Q8_00.0 GB 0.6 GB
Fits Get file →
—0.1 GB 0.6 GB
Fits Get file →

For 8 GB VRAM, Q2_K or Q4_0 are suitable, each 0.03 GB with ~0.6 GB memory at 8k context. If more memory is available, Q6_K or Q8_0 provide higher precision. The unknown quant is larger at 0.07 GB.

What GPU do you need for jina reranker v1 tiny en?

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 (0.1 GB file, about 0.6 GB in use).

Which jina reranker v1 tiny en quant should you choose?

Q4_K_M is the usual starting point for jina reranker v1 tiny en: it balances file size and quality well. Here it is a 0.0 GB file.

The Q8_0 file is 0.0 GB, about 1.1 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 0.0 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
Parameters33M
Layers4
Trained context8,192 tokens
KV cache (fp16)6 KB per token

Source

Quantized bygpustack
FamilyJina
Licenseapache-2.0
Downloads (HF)2,214
Last updated2025-01-15

Frequently asked questions about jina reranker v1 tiny en

How much VRAM does jina reranker v1 tiny en need?

About 0.6 GB at Q4_K_M with an 8K context window. That is the 0.0 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 v1 tiny en on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of jina reranker v1 tiny en GGUF?

It depends on the quant: Q2_K is 0.0 GB, Q4_0 is 0.0 GB, Q3_K_M is 0.0 GB, Q5_0 is 0.0 GB, Q4_K_M is 0.0 GB, Q5_K_M is 0.0 GB and 3 more.

What context length does jina reranker v1 tiny en support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.1 GB at 8K.

Where can I download jina reranker v1 tiny en GGUF?

The files are on Hugging Face in the gpustack/jina-reranker-v1-tiny-en-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 v1 tiny en 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, the Q2_K and Q4_0 quantizations use about 0.6 GB memory at 8k context, fitting easily in 8 GB VRAM.

Does it support image inputs?

No, the model only processes text and has no vision capabilities.

What license applies?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from gpustack

All by gpustack →

More Jina models

All Jina →

Other tiny models

All tiny models →