Instructions to use cstr/embeddinggemma-300m-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cstr/embeddinggemma-300m-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cstr/embeddinggemma-300m-GGUF",
	filename="embeddinggemma-300m-q4_k.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use cstr/embeddinggemma-300m-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cstr/embeddinggemma-300m-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf cstr/embeddinggemma-300m-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cstr/embeddinggemma-300m-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf cstr/embeddinggemma-300m-GGUF:Q8_0

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 cstr/embeddinggemma-300m-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf cstr/embeddinggemma-300m-GGUF:Q8_0

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 cstr/embeddinggemma-300m-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cstr/embeddinggemma-300m-GGUF:Q8_0

Use Docker

docker model run hf.co/cstr/embeddinggemma-300m-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use cstr/embeddinggemma-300m-GGUF with Ollama:
```
ollama run hf.co/cstr/embeddinggemma-300m-GGUF:Q8_0
```

Unsloth Studio new

How to use cstr/embeddinggemma-300m-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 cstr/embeddinggemma-300m-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 cstr/embeddinggemma-300m-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cstr/embeddinggemma-300m-GGUF to start chatting

Docker Model Runner
How to use cstr/embeddinggemma-300m-GGUF with Docker Model Runner:
```
docker model run hf.co/cstr/embeddinggemma-300m-GGUF:Q8_0
```

Lemonade

How to use cstr/embeddinggemma-300m-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cstr/embeddinggemma-300m-GGUF:Q8_0

Run and chat with the model

lemonade run user.embeddinggemma-300m-GGUF-Q8_0

List all available models

lemonade list

embeddinggemma-300m GGUF

GGUF format of google/embeddinggemma-300m for use with CrispEmbed and Ollama-compatible runtimes.

Google EmbeddingGemma 300M. Lightweight multilingual embedding model based on Gemma 3, optimized for search, retrieval, and semantic similarity across 100+ languages.

Model details

Architecture: Gemma 3 transformer (300M params), bidirectional attention
Pooling: Mean pooling + Dense projection (768→3072→768) + L2 normalize
Embedding dimension: 768
Languages: 100+ languages
Context length: 2,048 tokens
License: Gemma

Files

File	Quantization	Size	Parity (cos vs HF)
embeddinggemma-300m.gguf	F32	~1.2 GB	1.0000
embeddinggemma-300m-q8_0.gguf	Q8_0	~327 MB	0.9998
embeddinggemma-300m-q5_k.gguf	Q5_K	~289 MB	0.9954
embeddinggemma-300m-q4_k.gguf	Q4_K	~277 MB	0.9834

Q4_K shows mild degradation (~1.7%) which is typical for 4-bit quantization on embedding models. Use Q8_0 or Q5_K if highest fidelity is needed.

Quick Start

# With CrispEmbed
crispembed -m embeddinggemma-300m.gguf "Hello world"

See CrispEmbed for full documentation.

Notes

These GGUFs use the Ollama-compatible format with CrispEmbed extension keys:

gemma3.is_bidirectional = 1 — bidirectional (no causal mask)
gemma3.pooling_type = 1 — mean pooling
gemma3.rope.freq_base_local = 10000.0 — sliding-window RoPE theta
Dense projection weights stored in F32 for correctness across all quant levels

Downloads last month: 685

GGUF

Model size

0.3B params

Architecture

gemma3

Hardware compatibility

8-bit

View +1 variant

Model tree for cstr/embeddinggemma-300m-GGUF

Base model

google/embeddinggemma-300m

Quantized

(45)

this model