RUN THIS LLM
Search local LLM hardware requirements
EmbeddingGemma 300M
Google · 300M · Embedding
300M embedding model built from Gemma 3. Runs on-device — 100+ languages, Matryoshka dims from 128 to 768.
VRAM Requirements
| Quantization | VRAM |
|---|---|
| FP16 (full quality) | 0.6 GB |
Specifications
- Parameters: 300M
- Category: Embedding
- System RAM: 2 GB minimum
- HuggingFace: google/embeddinggemma-300m
Benchmarks
- MTEB: 61 — Embedding retrieval quality (avg)
Loading interactive analysis...