Downloads · 30 days
235
15% of all-time downloads
arctic-embed-m-v2-GGUF
cstr/arctic-embed-m-v2-GGUF
arctic-embed-m-v2-GGUF is a feature extraction model from cstr. Use it when you need embeddings to search or compare text. The card lists the license as apache-2.0.
GGUF format of Snowflake/snowflake-arctic-embed-m-v2.0 for use with CrispEmbed.
All-time downloads
1.6K
Public
Repo size
2.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf2.9 GB · 100%
At a glance
- Task
- Feature Extraction
- License
- apache-2.0
- Access
- Public
- Created
- Aug 4, 2026
- Updated
- Aug 5, 2026
- SHA
- f763149e
Base models
Model card
From the Hugging Face model README
arctic-embed-m-v2 GGUF
GGUF format of Snowflake/snowflake-arctic-embed-m-v2.0 for use with CrispEmbed.
Snowflake Arctic Embed M v2.0. Multilingual retrieval embeddings, 768-dimensional, 8192-token context. Queries take the prefix "query: "; documents take no prefix.
Files
| File | Quantization | Size |
|---|---|---|
| arctic-embed-m-v2-q4_k.gguf | Q4_K | 261 MB |
| arctic-embed-m-v2-q8_0.gguf | Q8_0 | 315 MB |
| arctic-embed-m-v2.gguf | F32 | 1170 MB |
Quick Start
# Download
huggingface-cli download cstr/arctic-embed-m-v2-GGUF arctic-embed-m-v2-q4_k.gguf --local-dir .
# Run with CrispEmbed
./crispembed -m arctic-embed-m-v2-q4_k.gguf "Hello world"
# Or with auto-download
./crispembed -m arctic-embed-m-v2 "Hello world"
Model Details
| Property | Value |
|---|---|
| Architecture | GTE v1.5 (RoPE, GeGLU, post-LN) |
| Parameters | 305M |
| Embedding Dimension | 768 |
| Layers | 12 |
| Pooling | CLS |
| Tokenizer | SentencePiece |
| Base Model | Snowflake/snowflake-arctic-embed-m-v2.0 |
Verification
Verified bit-identical to HuggingFace sentence-transformers (cosine similarity >= 0.999 on test texts).
Usage with CrispEmbed
CrispEmbed is a lightweight C/C++ text embedding inference engine using ggml. No Python runtime, no ONNX. Supports BERT, XLM-R, Qwen3, and Gemma3 architectures.
# Build CrispEmbed
git clone https://github.com/CrispStrobe/CrispEmbed
cd CrispEmbed
cmake -S . -B build && cmake --build build -j
# Encode
./build/crispembed -m arctic-embed-m-v2-q4_k.gguf "query text"
# Server mode
./build/crispembed-server -m arctic-embed-m-v2-q4_k.gguf --port 8080
curl -X POST http://localhost:8080/v1/embeddings \
-d '{"input": ["Hello world"], "model": "arctic-embed-m-v2"}'
Credits
- Original model: Snowflake/snowflake-arctic-embed-m-v2.0
- Inference engine: CrispEmbed (ggml-based)
- Conversion:
convert-bert-embed-to-gguf.py
- Task
- Feature Extraction
- License
- apache-2.0
- Languages
- multilingual
- Created
- Aug 4, 2026
- Updated
- Aug 5, 2026