---
license: apache-2.0
language: [multilingual]
tags: [embeddings, gguf, ggml, text-embeddings, qwen3, crispembed]
pipeline_tag: feature-extraction
base_model: Qwen/Qwen3-Embedding-8B
---

# qwen3-embed-8b GGUF

GGUF format of [Qwen/Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B) for use with [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed).

Qwen3 Embedding 8B. Official Alibaba embedding model, 4096-dimensional last-token pooling.

## Files

| File | Quantization | Size |
|------|-------------|------|
| [qwen3-embed-8b-q4_k.gguf](https://huggingface.co/cstr/qwen3-embed-8b-GGUF/resolve/main/qwen3-embed-8b-q4_k.gguf) | Q4_K | 4362 MB |
| [qwen3-embed-8b-q5_k.gguf](https://huggingface.co/cstr/qwen3-embed-8b-GGUF/resolve/main/qwen3-embed-8b-q5_k.gguf) | Q5_K | 5190 MB |
| [qwen3-embed-8b-q8_0.gguf](https://huggingface.co/cstr/qwen3-embed-8b-GGUF/resolve/main/qwen3-embed-8b-q8_0.gguf) | Q8_0 | 7674 MB |
| [qwen3-embed-8b.gguf](https://huggingface.co/cstr/qwen3-embed-8b-GGUF/resolve/main/qwen3-embed-8b.gguf) | F32 | 28873 MB |



## Quick Start

```bash
# Download
huggingface-cli download cstr/qwen3-embed-8b-GGUF qwen3-embed-8b-q4_k.gguf --local-dir .

# Run with CrispEmbed
./crispembed -m qwen3-embed-8b-q4_k.gguf "Hello world"

# Or with auto-download
./crispembed -m qwen3-embed-8b "Hello world"
```

## Model Details

| Property | Value |
|----------|-------|
| Architecture | Qwen3 |
| Parameters | 8B |
| Embedding Dimension | 4096 |
| Layers | 36 |
| Pooling | last-token |
| Tokenizer | GPT-2 BPE |
| Base Model | [Qwen/Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B) |

## 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 qwen3-embed-8b-q4_k.gguf "query text"

# Server mode
./build/crispembed-server -m qwen3-embed-8b-q4_k.gguf --port 8080
curl -X POST http://localhost:8080/v1/embeddings \
    -d '{"input": ["Hello world"], "model": "qwen3-embed-8b"}'
```

## Credits

- Original model: [Qwen/Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B)
- Inference engine: [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed) (ggml-based)
- Conversion: `convert-decoder-embed-to-gguf.py`