Zen Embedding 8B GGUF
High-performance text embedding model based on Qwen3-Embedding-8B, optimized for efficient inference.
Downloads
| Source | URL |
|---|---|
| HuggingFace | hf download zenlm/zen-embedding-8B-GGUF |
| Direct | https://download.hanzo.ai/llm-models/zen-embedding-8B-Q4_K_M.gguf |
Features
- 100+ language support
- #1 on MTEB multilingual leaderboard
- Optimized for semantic search and retrieval
- GGUF format for efficient CPU/GPU inference
- Q4_K_M quantization (4.68 GB)
Usage
Works with llama.cpp and compatible inference engines.
License
Apache 2.0 (inherited from Qwen3-Embedding)
- Downloads last month
- 77
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support