arctic-embed-l-v2 GGUF

GGUF format of Snowflake/snowflake-arctic-embed-l-v2.0 for use with CrispEmbed and Ollama.

Files

File	Quantization	Size
arctic-embed-l-v2-q4_k.gguf	Q4_K	0 MB
arctic-embed-l-v2-q8_0.gguf	Q8_0	0 MB
arctic-embed-l-v2.gguf	F32	0 MB

Recommended: Q8_0 for quality (cos vs HF: L2=1.0), Q4_K for size (L2=1.0).

Quick Start

CrispEmbed

./crispembed -m arctic-embed-l-v2 "Hello world"
./crispembed-server -m arctic-embed-l-v2 --port 8080

Ollama (with CrispStrobe fork)

echo "FROM arctic-embed-l-v2-q8_0.gguf" > Modelfile
ollama create arctic-embed-l-v2 -f Modelfile
curl http://localhost:11434/api/embed -d '{"model":"arctic-embed-l-v2","input":["Hello world"]}'

Python (CrispEmbed)

from crispembed import CrispEmbed
model = CrispEmbed("arctic-embed-l-v2-q8_0.gguf")
vectors = model.encode(["Hello world", "Goodbye world"])

Model Details

Property	Value
Architecture	XLM-R
Parameters	560M
Embedding Dimension	1024
Layers	24
Pooling	CLS
Tokenizer	SentencePiece
Language	en
Q8_0 vs HuggingFace	L2=1.0
Q4_K vs HuggingFace	L2=1.0