EM

Embeddinggemma 300m Qat Q4_0 Unquantized

EmbeddinggemmaGGUF by unslothUpdated 2025-09-04
Download on Hugging Face
Parameters303M
Context2K
Layers24
Architecturegemma-embedding
Smallest quant0.3 GB
Quick answer

Embeddinggemma 300m Qat Q4_0 Unquantized 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. This repository has 4 quants, from 0.3 GB (Q4_0) to 1.2 GB (F32).

EmbeddingGemma 300M: lightweight embedding model for text representation

EmbeddingGemma is a 300M parameter embedding model built from Gemma 3. It produces 768‑dimensional vectors and supports smaller sizes via Matryoshka Representation Learning. The model is optimized for on‑device use and supports up to 2048 tokens of context.

Good at

  • Fast embeddings on limited hardware
  • Supports 768/512/256/128 vector sizes
  • Compatible with Sentence Transformers

Limits

  • No vision or generation capabilities
  • Requires float32 or bfloat16 activations
  • Context limited to 2048 tokens

Best for

  • Semantic search indexing
  • Text classification feature extraction
  • Clustering and similarity search

Who it’s for. Developers needing efficient text embeddings on mobile or edge devices. Researchers and product teams looking for a small, open embedding model that can be run locally without large GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.3 GB 0.8 GB
Fits Get file →
Q8_00.3 GB 0.9 GB
Fits Get file →
BF160.6 GB 1.2 GB
Fits Get file →
F321.2 GB 1.8 GB
Fits Get file →

For 8 GB VRAM, use the Q4_0 quantized file (0.28 GB, ~1 GB memory at 8k context). If more memory is available, Q8_0 (0.33 GB) or BF16 (0.61 GB) provide higher precision. The unquantized model is 1.22 GB and requires ~1.9 GB memory.

What GPU do you need for Embeddinggemma 300m Qat Q4_0 Unquantized?

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 F32 (1.2 GB file, about 1.9 GB in use).

Which Embeddinggemma 300m Qat Q4_0 Unquantized 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.

If memory is tight, the smallest file is Q4_0 at 0.3 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

Architecturegemma-embedding
Parameters303M
Layers24
Trained context2,048 tokens
KV cache (fp16)24 KB per token

Source

Quantized byunsloth
Licensegemma
Downloads (HF)11,869
Last updated2025-09-04

Frequently asked questions about Embeddinggemma 300m Qat Q4_0 Unquantized

How much VRAM does Embeddinggemma 300m Qat Q4_0 Unquantized 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 Qat Q4_0 Unquantized on an 8 GB GPU?

Yes, with F32: the 1.2 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Embeddinggemma 300m Qat Q4_0 Unquantized GGUF?

It depends on the quant: Q4_0 is 0.3 GB, Q8_0 is 0.3 GB, BF16 is 0.6 GB, F32 is 1.2 GB.

What context length does Embeddinggemma 300m Qat Q4_0 Unquantized 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 Qat Q4_0 Unquantized GGUF?

The files are on Hugging Face in the unsloth/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 Qat Q4_0 Unquantized 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 on 8 GB VRAM?

Yes, the Q4_0 quantized version uses about 1 GB of VRAM at 8k context, fitting comfortably in 8 GB.

Does this model support float16 activations?

No, activations must be float32 or bfloat16; float16 is not supported.

What is the maximum context length for embeddings?

The model accepts up to 2048 tokens of input context.

Other GGUFs of embeddinggemma-300m

Similar models

Browse all →

More from unsloth

All by unsloth →

More Embeddinggemma models

All Embeddinggemma →

Other tiny models

All tiny models →