cstr/arctic-embed-l-v2-GGUF

arctic-embed-l-v2 GGUF

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

Files

Recommended: Q80 for quality (cos vs HF: L2=1.0), Q4K 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

Server API

CrispEmbed server supports four API dialects:

• —POST /embed -- native
• —POST /v1/embeddings -- OpenAI-compatible
• —POST /api/embed -- Ollama-compatible
• —POST /api/embeddings -- Ollama legacy

Credits

• —Original model: Snowflake/snowflake-arctic-embed-l-v2.0
• —Inference: CrispEmbed (MIT, ggml-based)

Provenance and EU AI Act Art. 53 note

• —Upstream model: Snowflake/snowflake-arctic-embed-l-v2.0 — published by Snowflake.
• —Upstream licence: apache-2.0. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
• —What was done here: format conversion and/or quantisation only (GGUF/GGML). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
• —Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository. No training-content summary was found on the upstream model card at the time of writing; that documentation gap is upstream's and is not filled here.
• —Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.