Sakura EmbeddingGemma 2 HighQuality needs about 0.7 GB of memory at its main file (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.0 GB to 0.2 GB.
Multimodal embedding model with 768‑dimensional vectors
Sakura EmbeddingGemma 2 HighQuality is a GGUF quantized version of google/embeddinggemma-2. It supports text, images, video, and audio embeddings in a unified 768‑dimensional space. The model is licensed under Apache‑2.0 and designed for low‑latency on consumer hardware.
Good at
- Multimodal embeddings
- Low‑latency on-device inference
- Flexible modality loading
Limits
- No vision support in this build
- Limited to 8K token context
- Requires 8‑bit or higher precision
Best for
- Search and retrieval systems
- Semantic similarity tasks
- Embedding generation for clustering
Who it’s for. Developers building on‑device search or RAG applications that need multimodal embeddings. The model is suitable for mobile and laptop environments with modest VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.2 GB | 0.7 GB | Fits | Get file → | |
| — | 0.2 GB | 0.7 GB | Fits | Get file → | |
| — | 0.2 GB | 0.7 GB | Fits | Get file → | |
| — | 0.2 GB | 0.7 GB | Fits | Get file → | |
| — | 0.2 GB | 0.8 GB | Fits | Get file → |
For 8‑GB VRAM, the 0.18‑GB file with 0.7‑GB memory at 8K context is suitable. If more memory is available, the 0.24‑GB file uses 0.8‑GB memory and may offer better precision. All estimates are approximate.
What GPU do you need for Sakura EmbeddingGemma 2 HighQuality?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.8 GB in use).
Which Sakura EmbeddingGemma 2 HighQuality quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Sakura EmbeddingGemma 2 HighQuality
How much VRAM does Sakura EmbeddingGemma 2 HighQuality need?
About 0.7 GB at its main file with an 8K context window. That is the 0.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Sakura EmbeddingGemma 2 HighQuality on an 8 GB GPU?
Yes, with the smaller files: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sakura EmbeddingGemma 2 HighQuality GGUF?
It depends on the quant: file is 0.0 GB, file is 0.2 GB, file is 0.2 GB, file is 0.2 GB, file is 0.2 GB, file is 0.2 GB.
Where can I download Sakura EmbeddingGemma 2 HighQuality GGUF?
The files are on Hugging Face in the webmp3/Sakura-EmbeddingGemma-2-HighQuality-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Sakura EmbeddingGemma 2 HighQuality use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, the 0.18‑GB quantization uses about 0.7‑GB memory at 8K context, fitting within 8‑GB VRAM.
Does this model support vision inputs?
The provided GGUF files do not include vision encoders; only text embeddings are available.
What license applies to this model?
The model is released under the Apache‑2.0 license.