EmbeddingGemma 2 Artemis text embeddings needs about 2.3 GB of memory at Q4_K_S (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.2 GB (Q4_K_S) to 0.2 GB (Q5_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
EmbeddingGemma 2 Artemis: 768‑dimensional text embeddings on consumer hardware
EmbeddingGemma 2 Artemis is a 0.271 billion‑parameter embedding model based on Gemma‑embedding2. It maps text into a 768‑dimensional vector space and supports multimodal inputs. The model is quantized for efficient CPU inference via llama.cpp.
Good at
- Fast text embeddings on CPUs
- Low‑latency semantic search
- Multilingual support
Limits
- No vision or audio inference in this GGUF file
- 8K token context only
- Requires CPU, not GPU
Best for
- Search engines
- Retrieval‑augmented generation
- Classification tasks
Who it’s for. Developers building on‑device search or RAG applications who need lightweight embeddings and can run on a CPU. The model is open‑source under Apache‑2.0 and can be integrated with llama.cpp or Ollama.
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 → |
For a 512‑MB download, use Q4_K_S (0.16 GB) which needs about 2.3 GB RAM at 8K context. If you need slightly higher quality, Q5_K_S (0.18 GB) also uses ~2.3 GB RAM. Both are suitable for CPUs with at least 4 GB of RAM.
What GPU do you need for EmbeddingGemma 2 Artemis text embeddings?
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 Q5_K_S (0.2 GB file, about 2.3 GB in use).
Which EmbeddingGemma 2 Artemis text embeddings quant should you choose?
Q4_K_S (0.2 GB) is the middle option in this repository. 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 Artemis text embeddings
How much VRAM does EmbeddingGemma 2 Artemis text embeddings need?
About 2.3 GB at Q4_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 Artemis text embeddings on an 8 GB GPU?
Yes, with Q5_K_S: the 0.2 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of EmbeddingGemma 2 Artemis text embeddings GGUF?
It depends on the quant: Q4_K_S is 0.2 GB, Q5_K_S is 0.2 GB.
What context length does EmbeddingGemma 2 Artemis text embeddings 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 Artemis text embeddings GGUF?
The files are on Hugging Face in the turintech/embeddinggemma-2-Artemis-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 Artemis text embeddings 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 EmbeddingGemma 2 Artemis on a CPU with 4 threads?
Yes, the model has been tested on a Linux CPU with four threads and a 512‑token input cap.
What is the vector dimensionality of the embeddings?
The embeddings are 768‑dimensional.
Does this GGUF file support vision or audio modalities?
No, the provided GGUF files only support text embeddings.