JI

jina-reranker-v3

JinaGGUF by jinaaiUpdated 2025-10-04
Download on Hugging Face
Parameters596M
Context128K
Layers28
Architectureqwen3
Smallest quant0.2 GB
Quick answer

jina-reranker-v3 needs about 1.8 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 18 quants, from 0.2 GB (IQ1_S) to 1.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

0.6B parameter multilingual listwise document reranker

jina-reranker-v3 is a 0.6B parameter multilingual document reranker built on Qwen3-0.6B. It processes up to 64 documents in a 131072 token context window and outputs relevance scores and optional embeddings.

Good at

  • Multilingual document reranking
  • Listwise inference
  • Embedding extraction

Limits

  • No vision support
  • CC BY-NC 4.0 license
  • Requires 8K context for memory estimates

Best for

  • Search engine ranking
  • Information retrieval pipelines
  • Academic research on BEIR benchmarks

Who it’s for. Developers building search or retrieval systems that need efficient, multilingual reranking. Researchers evaluating listwise rerankers on benchmark datasets. Teams requiring embeddings for downstream tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.2 GB 1.6 GB
Fits Get file →
IQ1_M0.2 GB 1.7 GB
Fits Get file →
IQ2_XXS0.2 GB 1.7 GB
Fits Get file →
IQ2_M0.3 GB 1.7 GB
Fits Get file →
IQ3_XXS0.3 GB 1.7 GB
Fits Get file →
Q2_K0.3 GB 1.7 GB
Fits Get file →
IQ3_XS0.3 GB 1.8 GB
Fits Get file →
IQ3_S0.3 GB 1.8 GB
Fits Get file →
IQ3_M0.3 GB 1.8 GB
Fits Get file →
Q3_K_M0.3 GB 1.8 GB
Fits Get file →
IQ4_XS0.4 GB 1.8 GB
Fits Get file →
IQ4_NL0.4 GB 1.8 GB
Fits Get file →
Q4_K_M0.4 GB 1.8 GB
Fits Get file →
Q5_K_S0.4 GB 1.9 GB
Fits Get file →
Q5_K_M0.4 GB 1.9 GB
Fits Get file →
Q6_K0.5 GB 1.9 GB
Fits Get file →
Q8_00.6 GB 2.1 GB
Fits Get file →
BF161.2 GB 2.6 GB
Fits Get file →

For 8GB VRAM, use IQ4_NL (0.38GB, ~1.8GB memory) or Q4_K_M (0.40GB, ~1.8GB memory). For 4GB VRAM, IQ1_S (0.21GB, ~1.6GB memory) is recommended. Larger models like Q8_0 (0.64GB, ~2.1GB memory) need 12GB+ VRAM.

What GPU do you need for jina-reranker-v3?

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 BF16 (1.2 GB file, about 2.6 GB in use).

Which jina-reranker-v3 quant should you choose?

Q4_K_M is the usual starting point for jina-reranker-v3: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.6 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 IQ1_S 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

Architectureqwen3
Parameters596M
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized byjinaai
FamilyJina
Downloads (HF)921
Last updated2025-10-04

Frequently asked questions about jina-reranker-v3

How much VRAM does jina-reranker-v3 need?

About 1.8 GB at Q4_K_M with an 8K context window. That is the 0.4 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-v3 on an 8 GB GPU?

Yes, with BF16: the 1.2 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of jina-reranker-v3 GGUF?

It depends on the quant: IQ1_S is 0.2 GB, IQ1_M is 0.2 GB, IQ2_XXS is 0.2 GB, IQ2_M is 0.3 GB, IQ3_XXS is 0.3 GB, Q2_K is 0.3 GB and 12 more.

What context length does jina-reranker-v3 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download jina-reranker-v3 GGUF?

The files are on Hugging Face in the jinaai/jina-reranker-v3-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-v3 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 jina-reranker-v3 on 8 GB VRAM?

Yes, use IQ4_NL or Q4_K_M quantizations; they require about 1.8GB of VRAM at 8K context.

Does the model support image inputs?

No, the model only processes text queries and documents.

Is the model free for commercial use?

No, it is licensed under CC BY-NC 4.0, so commercial use requires permission.

Other GGUFs of jina-reranker-v3

Similar models

Browse all →

More from jinaai

All by jinaai →

More Jina models

All Jina →

Other tiny models

All tiny models →