---
license: gemma
pipeline_tag: sentence-similarity
library_name: sentence-transformers
base_model: google/embeddinggemma-300m
model_creator: google
model_name: embeddinggemma-300m
quantized_by: Second State Inc.
---

<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->

# embeddinggemma-300m-Embedding-GGUF

## Original Model

[google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m)

## Run with LlamaEdge

- LlamaEdge version: [v0.26.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.26.1) and above

- Prompt template

  - Prompt type: `embedding`

- Context size: `2048`

- Embedding size: `128, 256, 512, 768`

- Run as LlamaEdge service

  ```bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:embeddinggemma-300m-f16.gguf \
    llama-api-server.wasm \
    --prompt-template embedding \
    --ctx-size 768 \
    --model-name embeddinggemma-300m
  ```

## Quantized GGUF Models

| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [embeddinggemma-300m-Q2_K.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q2_K.gguf)     | Q2_K   | 2 | 212 MB| smallest, significant quality loss - not recommended for most purposes |
| [embeddinggemma-300m-Q3_K_L.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q3_K_L.gguf) | Q3_K_L | 3 | 227 MB| small, substantial quality loss |
| [embeddinggemma-300m-Q3_K_M.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q3_K_M.gguf) | Q3_K_M | 3 | 224 MB| very small, high quality loss |
| [embeddinggemma-300m-Q3_K_S.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q3_K_S.gguf) | Q3_K_S | 3 | 218 MB| very small, high quality loss |
| [embeddinggemma-300m-Q4_0.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q4_0.gguf)     | Q4_0   | 4 | 229 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [embeddinggemma-300m-Q4_K_M.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q4_K_M.gguf) | Q4_K_M | 4 | 236 MB| medium, balanced quality - recommended |
| [embeddinggemma-300m-Q4_K_S.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q4_K_S.gguf) | Q4_K_S | 4 | 232 MB| small, greater quality loss |
| [embeddinggemma-300m-Q5_0.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q5_0.gguf)     | Q5_0   | 5 | 242 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [embeddinggemma-300m-Q5_K_M.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q5_K_M.gguf) | Q5_K_M | 5 | 247 MB| large, very low quality loss - recommended |
| [embeddinggemma-300m-Q5_K_S.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q5_K_S.gguf) | Q5_K_S | 5 | 243 MB| large, low quality loss - recommended |
| [embeddinggemma-300m-Q6_K.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q6_K.gguf)     | Q6_K   | 6 | 260 MB| very large, extremely low quality loss |
| [embeddinggemma-300m-Q8_0.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q8_0.gguf)     | Q8_0   | 8 | 329 MB| very large, extremely low quality loss - not recommended |
| [embeddinggemma-300m-f16.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-f16.gguf)       | f16   | 16 | 616 MB| very large, extremely low quality loss - not recommended |

*Quantized with llama.cpp b6397*