Instructions to use prithivMLmods/EmbeddingGemma-2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/EmbeddingGemma-2-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("feature-extraction", model="prithivMLmods/EmbeddingGemma-2-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/EmbeddingGemma-2-GGUF", device_map="auto")

sentence-transformers

How to use prithivMLmods/EmbeddingGemma-2-GGUF with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("prithivMLmods/EmbeddingGemma-2-GGUF")

sentences = [
    "The weather is lovely today.",
    "It's so sunny outside!",
    "He drove to the stadium."
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/EmbeddingGemma-2-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 prithivMLmods/EmbeddingGemma-2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/EmbeddingGemma-2-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 prithivMLmods/EmbeddingGemma-2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/EmbeddingGemma-2-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 prithivMLmods/EmbeddingGemma-2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/EmbeddingGemma-2-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 prithivMLmods/EmbeddingGemma-2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/EmbeddingGemma-2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/EmbeddingGemma-2-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use prithivMLmods/EmbeddingGemma-2-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/EmbeddingGemma-2-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use prithivMLmods/EmbeddingGemma-2-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/EmbeddingGemma-2-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/EmbeddingGemma-2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/EmbeddingGemma-2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.EmbeddingGemma-2-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

EmbeddingGemma-2-GGUF

EmbeddingGemma 2 is an open 740M-parameter multimodal embedding model developed by Google DeepMind that maps text, code, images, video, and audio into a unified 768-dimensional embedding space. Built for efficient on-device and edge deployment, it supports 100+ languages, an 8K-token context window, task-specific representations, and Matryoshka Representation Learning with 128d, 256d, 512d, and 768d embeddings for flexible storage and retrieval. The model combines a 270M-parameter text backbone with independently loadable 170M vision and 300M audio encoders, enabling applications such as semantic search, RAG, classification, clustering, similarity matching, code retrieval, and multimodal retrieval across consumer hardware. embeddinggemma-2 on Hugging Face — google/embeddinggemma-2.

Model Files

File Name	Quant Type	File Size	File Link	Description
embeddinggemma-2.BF16.gguf	BF16	558 MB	Link	Full BF16 weights. Highest quality, largest file size.
embeddinggemma-2.Q3_K_L.gguf	Q3_K_L	154 MB	Link	Lower quality but usable, good for low RAM availability.
embeddinggemma-2.Q3_K_M.gguf	Q3_K_M	149 MB	Link	Low quality.
embeddinggemma-2.Q4_K_M.gguf	Q4_K_M	182 MB	Link	Good quality, default size for most use cases, recommended.
embeddinggemma-2.Q4_K_S.gguf	Q4_K_S	178 MB	Link	Slightly lower quality with more space savings, recommended.
embeddinggemma-2.Q5_K_M.gguf	Q5_K_M	213 MB	Link	High quality, recommended.
embeddinggemma-2.Q5_K_S.gguf	Q5_K_S	211 MB	Link	High quality, recommended.
embeddinggemma-2.Q6_K.gguf	Q6_K	246 MB	Link	Very high quality, near perfect, recommended.
embeddinggemma-2.mmproj-bf16.gguf	mmproj-bf16	982 MB	Link	Multimodal projection file in BF16 format. Used for vision/language models.

llama.cpp

LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp

Downloads last month: -

GGUF

Model size

0.3B params

Architecture

gemma-embedding2

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

16-bit

Model tree for prithivMLmods/EmbeddingGemma-2-GGUF

Base model

google/embeddinggemma-2

Quantized

(29)

this model

Collection including prithivMLmods/EmbeddingGemma-2-GGUF

October 2026

Collection

Collection of Collections and Models — October 2026 • 30 items • Updated about 4 hours ago • 1