HADES-Embed-700M-v1 - GGUF

Official GGUF quantized models for ProtikD1810/hades-embed-v1.

Available Quantizations

File Quantization Size Target Hardware & Performance
hades-embed-700m-v1-Q8_0.gguf Q8_0 (8-bit) 753 MB Near-lossless precision; recommended for edge deployment & RTX 4070 Ti
hades-embed-700m-v1-F16.gguf F16 (16-bit) 1.41 GB Full floating-point precision

Usage with llama.cpp

# Feature extraction via llama-embedding
./llama-embedding \
  -m hades-embed-700m-v1-Q8_0.gguf \
  -p "Instruct: Retrieve relevant scientific research.\nQuery: High-temperature superconducting lead films" \
  --embd-normalize 2

Usage with Ollama

ollama run hf.co/ProtikD1810/hades-embed-v1-GGUF:Q8_0
Downloads last month
156
GGUF
Model size
0.7B params
Architecture
qwen2
Hardware compatibility
Log In to add your hardware

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for ProtikD1810/hades-embed-v1-GGUF

Quantized
(1)
this model