jina v5 nano needs about 1.0 GB of memory at Q8_0 (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 (IQ4_XS) to 0.9 GB.
Compact 210M decoder model for multilingual text embeddings
jina v5 nano is a 210M parameter embedding model built on Qwen3 architecture. It supports up to 8192 context tokens and outputs 1024‑dimensional embeddings. The model is licensed under cc‑by‑nc‑4.0.
Good at
- Fast inference on small GPUs
- Low memory footprint
- Multilingual embeddings up to 8192 tokens
Limits
- No vision or generation capabilities
- Requires 8k context for full performance
- cc‑by‑nc‑4.0 license limits commercial use
Best for
- Embedding generation for search engines
- Semantic similarity tasks
- Low‑resource inference setups
Who it’s for. Developers needing efficient, multilingual embeddings without large GPU memory. Researchers building lightweight embedding pipelines. Teams using CrispEmbed or llama.cpp for inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 0.2 GB | 1.0 GB | Fits | Get file → | |
| Q4_K | 0.2 GB | 1.0 GB | Fits | Get file → | |
| Q4_K | 0.2 GB | 1.0 GB | Fits | Get file → | |
| Q5_K | 0.2 GB | 1.0 GB | Fits | Get file → | |
| Q8_0 | 0.2 GB | 1.0 GB | Fits | Get file → | |
| — | 0.9 GB | 1.7 GB | Fits | Get file → | |
| — | 0.9 GB | 1.7 GB | Fits | Get file → | |
| — | 0.9 GB | 1.7 GB | Fits | Get file → | |
| — | 0.9 GB | 1.7 GB | Fits | Get file → |
For 8GB VRAM, use IQ4_XS (0.17GB) or Q4_K (0.18GB) files; both estimate 1GB memory at 8k context. If more memory is available, Q5_K (0.19GB) or Q8_0 (0.23GB) provide higher precision. Unknown quant files are larger (0.85GB) and need ~1.7GB memory.
What GPU do you need for jina v5 nano?
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 (0.9 GB file, about 1.7 GB in use).
Which jina v5 nano quant should you choose?
Q8_0 (0.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is IQ4_XS at 0.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about jina v5 nano
How much VRAM does jina v5 nano need?
About 1.0 GB at Q8_0 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 v5 nano on an 8 GB GPU?
Yes, with the smaller files: the 0.9 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of jina v5 nano GGUF?
It depends on the quant: IQ4_XS is 0.2 GB, Q4_K is 0.2 GB, Q4_K is 0.2 GB, Q5_K is 0.2 GB, Q8_0 is 0.2 GB, file is 0.9 GB and 3 more.
What context length does jina v5 nano 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 v5 nano GGUF?
The files are on Hugging Face in the cstr/jina-v5-nano-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 v5 nano 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 v5 nano on 8 GB VRAM?
Yes, the IQ4_XS and Q4_K quantizations are about 0.17–0.18 GB and require roughly 1 GB of VRAM at 8k context, well within 8 GB.
Does this model support image inputs?
No, jina v5 nano is an embedding model for text only; it has no vision capabilities.
Is the model free for commercial use?
No, the cc‑by‑nc‑4.0 license allows non‑commercial use only; commercial use requires separate permission.