EM

embeddinggemma-2

EmbeddinggemmaGGUF by ggml-orgUpdated 2026-10-19
Download on Hugging Face
Parameters271M
Context256K
Layers24
Architecturegemma-embedding2
Smallest quant0.3 GB
Quick answer

embeddinggemma-2 needs about 2.4 GB of memory at Q8_0 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.3 GB (Q8_0) to 0.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

EmbeddingGemma 2 – 768‑dimensional multimodal embeddings on consumer hardware

EmbeddingGemma 2 is a 0.271 B parameter model that maps text, images, video, and audio into a unified 768‑dimensional vector space. It supports 8K token context and offers truncated embeddings down to 128 d. The model is released under Apache 2.0.

Good at

  • Multimodal embeddings for text, vision, audio, video
  • Low‑latency inference on mobile and laptop GPUs
  • Supports truncated vectors for storage savings

Limits

  • Requires 2.4 GB VRAM for Q8_0 at 8K context
  • No vision support in quantized files without vision encoder
  • License is Apache 2.0 – no commercial restrictions

Best for

  • Search and retrieval‑augmented generation
  • Classification and clustering tasks
  • On‑device semantic similarity

Who it’s for. Developers building on‑device search, RAG, or classification systems that need fast, multimodal embeddings. The model is suitable for mobile and laptop environments where GPU memory is limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.3 GB 2.4 GB
Fits Get file →
BF160.6 GB 2.7 GB
Fits Get file →

For 8 GB VRAM, use Q8_0 (0.31 GB file, ~2.4 GB VRAM). If 4 GB VRAM is available, BF16 (0.56 GB file, ~2.7 GB VRAM) is the next option. Both provide full multimodal capability; choose the smaller file for tighter memory budgets.

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 BF16 (0.6 GB file, about 2.7 GB in use).

Which embeddinggemma-2 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-embedding2
Parameters271M
Layers24
Trained context262,144 tokens
KV cache (fp16)192 KB per token

Source

Quantized byggml-org
Licenseapache-2.0
Downloads (HF)104,995
Last updated2026-10-19

Frequently asked questions about embeddinggemma-2

How much VRAM does embeddinggemma-2 need?

About 2.4 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-2 on an 8 GB GPU?

Yes, with BF16: the 0.6 GB file needs about 2.7 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: Q8_0 is 0.3 GB, BF16 is 0.6 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 ggml-org/embeddinggemma-2-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 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 on 4 GB VRAM?

The BF16 quant requires about 2.7 GB VRAM at 8K context, so it fits within a 4 GB budget. The Q8_0 quant uses ~2.4 GB VRAM, also fitting comfortably.

Does the model support vision?

Yes, EmbeddingGemma 2 includes a 170 M vision encoder that can be loaded when needed. The quantized files contain the vision module.

What is the context length?

The model supports an 8K token context window, allowing it to process long text or extended audio/video inputs.

Other GGUFs of embeddinggemma-2

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Embeddinggemma models

All Embeddinggemma →

Other tiny models

All tiny models →