Instructions to use second-state/jina-embeddings-v2-small-en-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use second-state/jina-embeddings-v2-small-en-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf second-state/jina-embeddings-v2-small-en-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/jina-embeddings-v2-small-en-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf second-state/jina-embeddings-v2-small-en-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/jina-embeddings-v2-small-en-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf second-state/jina-embeddings-v2-small-en-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/jina-embeddings-v2-small-en-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf second-state/jina-embeddings-v2-small-en-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/jina-embeddings-v2-small-en-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/jina-embeddings-v2-small-en-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use second-state/jina-embeddings-v2-small-en-GGUF with Ollama:
```
ollama run hf.co/second-state/jina-embeddings-v2-small-en-GGUF:Q4_K_M
```

Unsloth Studio

How to use second-state/jina-embeddings-v2-small-en-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for second-state/jina-embeddings-v2-small-en-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for second-state/jina-embeddings-v2-small-en-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for second-state/jina-embeddings-v2-small-en-GGUF to start chatting

Docker Model Runner
How to use second-state/jina-embeddings-v2-small-en-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/jina-embeddings-v2-small-en-GGUF:Q4_K_M
```

Lemonade

How to use second-state/jina-embeddings-v2-small-en-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/jina-embeddings-v2-small-en-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.jina-embeddings-v2-small-en-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

jina-embeddings-v2-small-en-GGUF

Original Model

jinaai/jina-embeddings-v2-small-en

Run with LlamaEdge

LlamaEdge version: v0.14.17
Prompt template
- Prompt type: embedding
Context size: 8192
Embedding dim: 512

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:jina-embeddings-v2-small-en-f16.gguf \
  llama-api-server.wasm \
  --prompt-template embedding \
  --ctx-size 8192 \
  --model-name jina-embeddings-v2-small-en

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
jina-embeddings-v2-small-en-Q2_K.gguf	Q2_K	2	19.7 MB	smallest, significant quality loss - not recommended for most purposes
jina-embeddings-v2-small-en-Q3_K_L.gguf	Q3_K_L	3	22.4 MB	small, substantial quality loss
jina-embeddings-v2-small-en-Q3_K_M.gguf	Q3_K_M	3	21.6 MB	very small, high quality loss
jina-embeddings-v2-small-en-Q3_K_S.gguf	Q3_K_S	3	20.7 MB	very small, high quality loss
jina-embeddings-v2-small-en-Q4_0.gguf	Q4_0	4	23.0 MB	legacy; small, very high quality loss - prefer using Q3_K_M
jina-embeddings-v2-small-en-Q4_K_M.gguf	Q4_K_M	4	23.6 MB	medium, balanced quality - recommended
jina-embeddings-v2-small-en-Q4_K_S.gguf	Q4_K_S	4	23.1 MB	small, greater quality loss
jina-embeddings-v2-small-en-Q5_0.gguf	Q5_0	5	25.1 MB	legacy; medium, balanced quality - prefer using Q4_K_M
jina-embeddings-v2-small-en-Q5_K_M.gguf	Q5_K_M	5	25.4 MB	large, very low quality loss - recommended
jina-embeddings-v2-small-en-Q5_K_S.gguf	Q5_K_S	5	25.1 MB	large, low quality loss - recommended
jina-embeddings-v2-small-en-Q6_K.gguf	Q6_K	6	27.3 MB	very large, extremely low quality loss
jina-embeddings-v2-small-en-Q8_0.gguf	Q8_0	8	35.1 MB	very large, extremely low quality loss - not recommended
jina-embeddings-v2-small-en-f16.gguf	f16	16	65.5 MB	very large, extremely low quality loss - not recommended

Quantized with llama.cpp b4273

Downloads last month: 170

GGUF

Model size

32.4M params

Architecture

jina-bert-v2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for second-state/jina-embeddings-v2-small-en-GGUF

Base model

jinaai/jina-embeddings-v2-small-en

Quantized

(8)

this model