Jina Reranker M0 needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 18 quants, from 0.4 GB (IQ1_S) to 3.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
Multilingual multimodal document reranker
Jina Reranker M0 is a decoder‑only vision‑language model fine‑tuned for ranking visual documents across 29+ languages. It processes up to 32768 tokens and supports images from 56×56 to 4K resolution. The model outputs relevance scores for query‑document pairs.
Good at
- Multimodal ranking
- Long‑context document handling
- Code search
Limits
- No vision support in some contexts
- Limited to 32768 tokens
- CC‑BY‑NC‑4.0 license
Best for
- Document retrieval systems
- Multilingual search engines
- Technical code search
Who it’s for. Developers building search or retrieval systems that need to rank visual documents in multiple languages. The model is suitable for applications requiring long‑context understanding and multimodal input.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.4 GB | 1.2 GB | Fits | Get file → | |
| IQ1_M | 0.5 GB | 1.2 GB | Fits | Get file → | |
| IQ2_XXS | 0.5 GB | 1.2 GB | Fits | Get file → | |
| IQ2_M | 0.6 GB | 1.3 GB | Fits | Get file → | |
| IQ3_XXS | 0.7 GB | 1.4 GB | Fits | Get file → | |
| Q2_K | 0.7 GB | 1.4 GB | Fits | Get file → | |
| IQ3_XS | 0.7 GB | 1.5 GB | Fits | Get file → | |
| IQ3_S | 0.8 GB | 1.5 GB | Fits | Get file → | |
| IQ3_M | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 0.8 GB | 1.6 GB | Fits | Get file → | |
| IQ4_XS | 0.9 GB | 1.6 GB | Fits | Get file → | |
| IQ4_NL | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_M | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_S | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_M | 1.1 GB | 1.9 GB | Fits | Get file → | |
| Q6_K | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q8_0 | 1.6 GB | 2.4 GB | Fits | Get file → | |
| F16 | 3.1 GB | 3.8 GB | Fits | Get file → |
For 8 GB VRAM, use IQ4_NL (0.94 GB) or Q4_K_M (0.99 GB); memory estimate is 1.7 GB at 8 k context. For 4 GB VRAM, IQ3_XXS (0.51 GB) or IQ2_M (0.6 GB) are recommended. Higher precision quants such as Q8_0 (1.65 GB) require at least 2.4 GB VRAM.
What GPU do you need for Jina Reranker M0?
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 (3.1 GB file, about 3.8 GB in use).
Which Jina Reranker M0 quant should you choose?
Q4_K_M is the usual starting point for Jina Reranker M0: it balances file size and quality well. Here it is a 1.0 GB file.
The Q8_0 file is 1.6 GB, about 1.7 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 0.4 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
Source
Frequently asked questions about Jina Reranker M0
How much VRAM does Jina Reranker M0 need?
About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 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 M0 on an 8 GB GPU?
Yes, with F16: the 3.1 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Jina Reranker M0 GGUF?
It depends on the quant: IQ1_S is 0.4 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.5 GB, IQ2_M is 0.6 GB, IQ3_XXS is 0.7 GB, Q2_K is 0.7 GB and 12 more.
What context length does Jina Reranker M0 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.
Where can I download Jina Reranker M0 GGUF?
The files are on Hugging Face in the jinaai/jina-reranker-m0-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 M0 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 M0 on 8 GB VRAM?
Yes, using IQ4_NL or Q4_K_M quants will fit within 8 GB VRAM, with an estimated 1.7 GB memory usage at 8 k context.
What is the maximum context length for this model?
The model supports up to 32768 tokens, enabling long document reranking.
Does the model support image inputs?
Yes, it accepts images from 56×56 to 4K resolution and processes them with dynamic patching.