---
license: cc-by-nc-4.0
language: [multilingual]
tags: [embeddings, gguf, ggml, text-embeddings, qwen3, crispembed]
pipeline_tag: feature-extraction
base_model: jinaai/jina-embeddings-v5-text-small
---

# jina-v5-small GGUF

GGUF format of [jinaai/jina-embeddings-v5-text-small](https://huggingface.co/jinaai/jina-embeddings-v5-text-small) for use with [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed).

Jina Embeddings v5 Small. Full-size decoder model, 1024-dimensional.

## Files

| File | Quantization | Size |
|------|-------------|------|
| [jina-v5-small-classification.gguf](https://huggingface.co/cstr/jina-v5-small-GGUF/resolve/main/jina-v5-small-classification.gguf) | F32 | 2279 MB |
| [jina-v5-small-clustering.gguf](https://huggingface.co/cstr/jina-v5-small-GGUF/resolve/main/jina-v5-small-clustering.gguf) | F32 | 2279 MB |
| [jina-v5-small-q4_k.gguf](https://huggingface.co/cstr/jina-v5-small-GGUF/resolve/main/jina-v5-small-q4_k.gguf) | Q4_K | 400 MB |
| [jina-v5-small-q5_k.gguf](https://huggingface.co/cstr/jina-v5-small-GGUF/resolve/main/jina-v5-small-q5_k.gguf) | Q5_K | 452 MB |
| [jina-v5-small-q8_0.gguf](https://huggingface.co/cstr/jina-v5-small-GGUF/resolve/main/jina-v5-small-q8_0.gguf) | Q8_0 | 610 MB |
| [jina-v5-small-text-matching.gguf](https://huggingface.co/cstr/jina-v5-small-GGUF/resolve/main/jina-v5-small-text-matching.gguf) | F32 | 2279 MB |
| [jina-v5-small.gguf](https://huggingface.co/cstr/jina-v5-small-GGUF/resolve/main/jina-v5-small.gguf) | F32 | 2279 MB |



## Quick Start

```bash
# Download
huggingface-cli download cstr/jina-v5-small-GGUF jina-v5-small-classification.gguf --local-dir .

# Run with CrispEmbed
./crispembed -m jina-v5-small-classification.gguf "Hello world"

# Or with auto-download
./crispembed -m jina-v5-small "Hello world"
```

## Model Details

| Property | Value |
|----------|-------|
| Architecture | Qwen3 |
| Parameters | 600M |
| Embedding Dimension | 1024 |
| Layers | 28 |
| Pooling | last-token |
| Tokenizer | GPT-2 BPE |
| Base Model | [jinaai/jina-embeddings-v5-text-small](https://huggingface.co/jinaai/jina-embeddings-v5-text-small) |

## Verification

Verified bit-identical to HuggingFace sentence-transformers (cosine similarity >= 0.999 on test texts).

## Usage with CrispEmbed

CrispEmbed is a lightweight C/C++ text embedding inference engine using ggml.
No Python runtime, no ONNX. Supports BERT, XLM-R, Qwen3, and Gemma3 architectures.

```bash
# Build CrispEmbed
git clone https://github.com/CrispStrobe/CrispEmbed
cd CrispEmbed
cmake -S . -B build && cmake --build build -j

# Encode
./build/crispembed -m jina-v5-small-classification.gguf "query text"

# Server mode
./build/crispembed-server -m jina-v5-small-classification.gguf --port 8080
curl -X POST http://localhost:8080/v1/embeddings \
    -d '{"input": ["Hello world"], "model": "jina-v5-small"}'
```

## Credits

- Original model: [jinaai/jina-embeddings-v5-text-small](https://huggingface.co/jinaai/jina-embeddings-v5-text-small)
- Inference engine: [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed) (ggml-based)
- Conversion: `convert-decoder-embed-to-gguf.py`