---
base_model: telepix/PIXIE-Rune-v1.0
tags:
  - gguf
  - embedding
  - korean
  - xlm-roberta
  - sentence-transformers
license: apache-2.0
---

# PIXIE-Rune-v1.0 GGUF

GGUF conversion of [telepix/PIXIE-Rune-v1.0](https://huggingface.co/telepix/PIXIE-Rune-v1.0).

**#2 on Korean Embedding Leaderboard** (NDCG@5,10 avg: 84.68)

## Files

| File | Quant | Size |
|------|-------|------|
| PIXIE-Rune-v1.0-Q8_0.gguf | Q8_0 | 599 MB |
| PIXIE-Rune-v1.0-F16.gguf | F16 | 1.15 GB |

## Usage with llama.cpp

```bash
llama-server -m PIXIE-Rune-v1.0-Q8_0.gguf --port 9020 --embedding --pooling mean
```

## Model Info
- Architecture: XLM-RoBERTa (24 layers, hidden=1024)
- Parameters: ~335M
- Embedding dimension: 1024
- Max sequence length: 8192