embeddinggemma-2 needs about 2.3 GB of memory at Q5_K_S (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.2 GB (Q4_K_S) to 0.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
EmbeddingGemma 2 – compact multimodal embedding model
EmbeddingGemma 2 maps text, images, video, and audio into a unified 768‑dimensional space. It has 0.271 billion parameters and supports a 8K token context window. The model is designed for low‑latency on consumer hardware.
Good at
- Multimodal embeddings
- Fast inference on mobile
- Low memory footprint
Limits
- No vision or audio support without loading optional encoders
- Limited to 8K context
- License: gemma
Best for
- Search and retrieval‑augmented generation
- Text classification and clustering
- On‑device semantic search
Who it’s for. Developers building on‑device semantic search or retrieval systems that require multimodal embeddings. The model is suitable for mobile and laptop environments where low latency and small memory usage are critical.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_S | 0.2 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_S | 0.2 GB | 2.3 GB | Fits | Get file → | |
| Q6_K | 0.2 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM use Q4_K_S (0.18 GB, ~2.3 GB memory at 8K context). For 12 GB VRAM use Q5_K_S (0.21 GB, ~2.3 GB memory). For 16 GB VRAM use Q6_K (0.24 GB, ~2.4 GB memory). Estimates are approximate.
What GPU do you need for embeddinggemma-2?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 Q6_K (0.2 GB file, about 2.4 GB in use).
Which embeddinggemma-2 quant should you choose?
Q5_K_S (0.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q4_K_S at 0.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about embeddinggemma-2
How much VRAM does embeddinggemma-2 need?
About 2.3 GB at Q5_K_S 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 embeddinggemma-2 on an 8 GB GPU?
Yes, with Q6_K: the 0.2 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of embeddinggemma-2 GGUF?
It depends on the quant: Q4_K_S is 0.2 GB, Q5_K_S is 0.2 GB, Q6_K is 0.2 GB.
What context length does embeddinggemma-2 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download embeddinggemma-2 GGUF?
The files are on Hugging Face in the webmp3/Sakura-EmbeddingGemma-2-AutoRound-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 embeddinggemma-2 use?
Hugging Face lists the license as gemma. 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 EmbeddingGemma 2 on 8 GB VRAM?
Yes, the Q4_K_S quantized model is 0.18 GB and requires about 2.3 GB of VRAM at 8K context.
Does the model support audio input?
Audio support is available through a separate 300M encoder that must be loaded separately.
What context length does the model support?
The model supports an 8K token context window.