jina embeddings v2 base zh needs about 0.9 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 0.1 GB (Q2_K) to 0.3 GB (F16).
Jina embeddings v2 base zh – 161 M‑parameter bilingual embedding model
Jina embeddings v2 base zh is a 161 million parameter model trained on Chinese and English text. It supports a context length of 8192 tokens and outputs 768‑dimensional embeddings. The model is available in multiple GGUF quantizations.
Good at
- Chinese‑English cross‑lingual embeddings
- Long‑sequence support up to 8192 tokens
- Efficient mean‑pooling for sentence vectors
Limits
- No vision or generation capabilities
- Requires 8192‑token context for full performance
- Apache‑2.0 license limits commercial use without attribution
Best for
- Multilingual document retrieval
- Cross‑lingual semantic search
- Embedding‑based clustering
Who it’s for. Developers building multilingual search or recommendation systems that need high‑quality embeddings for Chinese and English. Researchers requiring a lightweight, bilingual embedding model for experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.1 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_S | 0.1 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_M | 0.1 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_L | 0.1 GB | 0.9 GB | Fits | Get file → | |
| Q4_0 | 0.1 GB | 0.9 GB | Fits | Get file → | |
| Q4_K_S | 0.1 GB | 0.9 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.9 GB | Fits | Get file → | |
| Q5_0 | 0.1 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_S | 0.1 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.9 GB | Fits | Get file → | |
| Q6_K | 0.1 GB | 0.9 GB | Fits | Get file → | |
| Q8_0 | 0.2 GB | 1.0 GB | Fits | Get file → | |
| F16 | 0.3 GB | 1.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.11 GB file, ~0.9 GB memory). For 16 GB VRAM, Q8_0 (0.17 GB file, ~1 GB memory) or F16 (0.32 GB file, ~1.1 GB memory) provide higher precision. Choose the smallest file that meets your accuracy needs.
What GPU do you need for jina embeddings v2 base zh?
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 (0.3 GB file, about 1.1 GB in use).
Which jina embeddings v2 base zh quant should you choose?
Q4_K_M is the usual starting point for jina embeddings v2 base zh: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.2 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 Q2_K at 0.1 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 embeddings v2 base zh
How much VRAM does jina embeddings v2 base zh need?
About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.1 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 v2 base zh on an 8 GB GPU?
Yes, with F16: the 0.3 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of jina embeddings v2 base zh GGUF?
It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, Q4_0 is 0.1 GB, Q4_K_S is 0.1 GB and 7 more.
What context length does jina embeddings v2 base zh 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 embeddings v2 base zh GGUF?
The files are on Hugging Face in the second-state/jina-embeddings-v2-base-zh-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 v2 base zh 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 Q4_K_M quantization uses about 0.9 GB of VRAM at 8192 context, fitting within an 8 GB GPU.
Does this model support vision tasks?
No, it is a text‑only embedding model and does not process images.
What context length does it support?
The model supports up to 8192 tokens; longer inputs require truncation.