Jina Embeddings v3 needs about 1.7 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 0.0 GB (F16) to 1.1 GB (F16).
Jina Embeddings v3 – multilingual text embedding model
Jina Embeddings v3 is a multilingual, multi‑task embedding model based on the Jina‑BERT‑v3 architecture. It supports up to 8192 tokens with Rotary Position Embeddings and offers task‑specific LoRA adapters for retrieval, classification, and similarity tasks.
Good at
- Embedding generation for retrieval
- Multilingual support across 30+ languages
- Task‑specific embeddings via LoRA
Limits
- No vision support
- License cc‑by‑nc‑4.0 restricts commercial use
- Maximum context length 8192 tokens
Best for
- Search engine query embeddings
- Semantic clustering and re‑ranking
- Cross‑lingual similarity search
Who it’s for. Developers building search, recommendation, or classification systems that require multilingual embeddings. Researchers needing flexible embedding sizes and task‑specific tuning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.0 GB | 1.3 GB | Fits | Get file → | |
| F16 | 0.0 GB | 1.3 GB | Fits | Get file → | |
| F16 | 0.0 GB | 1.3 GB | Fits | Get file → | |
| F16 | 0.0 GB | 1.3 GB | Fits | Get file → | |
| F16 | 0.0 GB | 1.3 GB | Fits | Get file → | |
| Q2_K | 0.3 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_S | 0.3 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_M | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q4_0 | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_S | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_L | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_M | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q5_0 | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_S | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_M | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 0.5 GB | 1.8 GB | Fits | Get file → | |
| Q8_0 | 0.6 GB | 1.9 GB | Fits | Get file → | |
| F16 | 1.1 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.41 GB file, ~1.7 GB memory). For 4 GB VRAM, Q3_K_S (0.35 GB file, ~1.7 GB memory). For minimal VRAM, Q2_K (0.33 GB file, ~1.6 GB memory). File sizes are approximate and memory estimates are at 8k context.
What GPU do you need for Jina Embeddings 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 F16 (1.1 GB file, about 2.4 GB in use).
Which Jina Embeddings v3 quant should you choose?
Q4_K_M is the usual starting point for Jina Embeddings 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 1.5 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 F16 at 0.0 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Jina Embeddings v3
How much VRAM does Jina Embeddings v3 need?
About 1.7 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 Embeddings v3 on an 8 GB GPU?
Yes, with F16: the 1.1 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Jina Embeddings v3 GGUF?
It depends on the quant: F16 is 0.0 GB, F16 is 0.0 GB, F16 is 0.0 GB, F16 is 0.0 GB, F16 is 0.0 GB, Q2_K is 0.3 GB and 12 more.
What context length does Jina Embeddings v3 support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.8 GB at 8K.
Where can I download Jina Embeddings v3 GGUF?
The files are on Hugging Face in the second-state/jina-embeddings-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 Embeddings 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 Embeddings v3 on 8 GB VRAM?
Yes, using Q4_K_M or Q4_K_S quantizations requires about 1.7 GB of VRAM at 8k context.
Does the model support image inputs?
No, Jina Embeddings v3 is a text‑only embedding model.
What license applies to this model?
The model is licensed under cc‑by‑nc‑4.0, allowing non‑commercial use with attribution.