EM

Embeddinggemma 300m

EmbeddinggemmaGGUF by ggml-orgUpdated 2026-04-29
Download on Hugging Face
Parameters308M
Context2K
Layers24
Architecturegemma-embedding
Smallest quant0.3 GB
Quick answer

Embeddinggemma 300m needs about 1.0 GB of memory at Q8_0 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Embeddinggemma 300m – lightweight embedding model

Embeddinggemma 300m is a 0.3 billion‑parameter embedding model based on the Gemma architecture. It supports a 2048‑token context window and is optimized for generating embeddings. The model is available in a single Q8_0 quantized GGUF file.

Good at

  • Fast embedding generation
  • Low memory footprint
  • Easy integration with llama.cpp

Limits

  • No text generation capability
  • No vision support
  • Requires 1 GB VRAM at 8 k context

Best for

  • Semantic search indexing
  • Vector similarity retrieval
  • Embedding‑based clustering

Who it’s for. Developers building search engines or recommendation systems that need efficient, high‑quality embeddings. Suitable for edge deployments with limited GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.3 GB 0.9 GB
Fits Get file →

The only available quant is Q8_0, 0.33 GB in size. It requires about 1 GB VRAM at 8 k context, which is suitable for GPUs with 2 GB or more. No other quantizations are provided.

What GPU do you need for Embeddinggemma 300m?

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 Q8_0 (0.3 GB file, about 1.0 GB in use).

Which Embeddinggemma 300m quant should you choose?

Q8_0 (0.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma-embedding
Parameters308M
Layers24
Trained context2,048 tokens
KV cache (fp16)24 KB per token

Source

Quantized byggml-org
Licensegemma
Downloads (HF)380,228
Last updated2026-04-29

Frequently asked questions about Embeddinggemma 300m

How much VRAM does Embeddinggemma 300m need?

About 1.0 GB at Q8_0 with an 8K context window. That is the 0.3 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 300m on an 8 GB GPU?

Yes, with Q8_0: the 0.3 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Embeddinggemma 300m GGUF?

It depends on the quant: Q8_0 is 0.3 GB.

What context length does Embeddinggemma 300m support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.1 GB at 2K.

Where can I download Embeddinggemma 300m GGUF?

The files are on Hugging Face in the ggml-org/embeddinggemma-300M-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 300m 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 this model on 8 GB VRAM?

Yes, the Q8_0 quant requires only about 1 GB VRAM at 8 k context, leaving ample memory for other processes.

Does this model support text generation?

No, it is designed solely for embedding generation and does not produce text.

What is the context length of this model?

It supports a maximum context length of 2048 tokens.

Other GGUFs of embeddinggemma-300m

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Embeddinggemma models

All Embeddinggemma →

Other tiny models

All tiny models →