cstr/embeddinggemma-300m-GGUF

embeddinggemma-300m GGUF

GGUF format of google/embeddinggemma-300m for use with CrispEmbed.

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)
• Embedding dimension: 768 (Matryoshka: 512, 256, 128)
• Languages: 100+ languages
• Context length: 2,048 tokens
• License: Gemma

Files

File	Quantization	Size
embeddinggemma-300m.gguf	F32	~1.1 GB
embeddinggemma-300m-q8_0.gguf	Q8_0	~300 MB
embeddinggemma-300m-q4_k.gguf	Q4_K	~170 MB

Quick Start

See CrispEmbed for full documentation and CrispASR for speech-to-text.