Title: EmbeddingGemma 300M %E2%80%94 embeddinggemma-300m
Canonical: https://llmeu.com/hr/models/embeddinggemma-300m/
Markdown mirror: https://llmeu.com/hr/models/embeddinggemma-300m.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json
Provider: Google DeepMind
Licence: gemma
Hosting: catalogue only %E2%80%94 not hosted on LLM EU yet
Sources: https://huggingface.co/google/embeddinggemma-300m https://arxiv.org/abs/2509.20354

# EmbeddingGemma 300M

[Google DeepMind](/hr/providers/google/)

Posljednji pregled: 14. lis 2026.

## Suverenost i hosting

Ovaj model je u katalogu za referencu. Jo%C5%A1 nije hostan na LLM EU i nijedan endpoint prvog lica ga ovdje ne poslu%C5%BEuje. Zahtjevi za njega idu izravno pru%C5%BEatelju, pod uvjetima tog pru%C5%BEatelja.

## Sa%C5%BEetak

EmbeddingGemma je model za ugradnju teksta s 308M parametara i 768-dimenzionalnim izlazom koji se mo%C5%BEe skratiti na 512, 256 ili 128 dimenzija putem Matryoshka reprezentacijskog u%C4%8Denja. Kartica modela navodi maksimalnu ulaznu duljinu od 2048 tokena i podatke za obuku na vi%C5%A1e od 100 govornih jezika. Objavljen je pod Googleovim Gemma uvjetima, a ne pod OSI licencom.

## Specifikacije

- Pru%C5%BEatelj
  Google DeepMind (US)
- Kontekstni prozor
  2.0k
- Parametri
  0.3B
- Modaliteti
  embedding
- Licenca
  gemma %C2%B7 [licence](https://ai.google.dev/gemma/terms)
- Otvoreni utezi
  yes
- Datum izdanja
  17. srp 2025.
- Zadaci
  [Dohva%C4%87anje (RAG)](/hr/tasks/rag/), [Vi%C5%A1ejezi%C4%8Dna podr%C5%A1ka](/hr/tasks/multilingual-support/), [Osjetljivi podaci](/hr/tasks/private/), [Niska cijena](/hr/tasks/cheap/)

## Jezici

**Jako:** en, de, fr, es, it, pt, nl, pl

**Zadovoljavaju%C4%87e:** sv, da, fi, cs, ro, el, uk, ru, ar, hi, zh, ja, ko, tr

#### Jako

- en
- de
- fr
- es
- it
- pt
- nl
- pl

#### Zadovoljavaju%C4%87e

- sv
- da
- fi
- cs
- ro
- el
- uk
- ru
- ar
- hi
- zh
- ja
- ko
- tr

Nije provjereno: pru%C5%BEatelj nije dokumentirao ovu tvrdnju. %E2%80%94 a language is listed as strong only where a source claims it; the card links the evidence where one exists.

## Kada ga koristiti

#### Prednosti

- flexible output dimensions for cheaper vector indexes
- small enough to embed on CPU
- training data in over 100 languages

#### Ograni%C4%8Denja

- 2048-token input limit
- Gemma terms of use, not an OSI-approved licence
- no retrieval benchmark has been run by LLM EU

## %C4%8Cesto postavljana pitanja

### Is EmbeddingGemma 300M served on LLM EU?

It has no endpoint in the catalogue, so it is catalogue only %E2%80%94 not hosted on LLM EU yet, with no region and no retention to report. A card whose status is "listed" is a catalogue entry, not a running deployment.

### Under what licence is EmbeddingGemma 300M released?

EmbeddingGemma 300M is recorded under gemma. The recorded licence text is https://ai.google.dev/gemma/terms. The weights are downloadable (open_weights is true). LLM EU republishes the licence id and the link and gives no legal advice; the licence text governs.

### How large is EmbeddingGemma 300M, and what context window does it have?

EmbeddingGemma 300M is recorded at 308M (safetensors total 302,863,104) (source: https://huggingface.co/api/models/google/embeddinggemma-300m), with a context window of 2048 tokens (source: https://huggingface.co/google/embeddinggemma-300m).

### Cijene

Ovaj model je u katalogu za referencu. Jo%C5%A1 nije hostan na LLM EU i nijedan endpoint prvog lica ga ovdje ne poslu%C5%BEuje. Zahtjevi za njega idu izravno pru%C5%BEatelju, pod uvjetima tog pru%C5%BEatelja.

### Status provjere

Kada polje nema izvor, kartica ga prikazuje kao neprovjereno umjesto da ga popuni. Prazno polje je informacija.

LLM EU Verified zna%C4%8Di dokumentirano, ne pravno certificirano. To nije procjena sukladnosti s AI Actom i LLM EU nije tijelo EU-a.

### Verzije i varijante

- catalogue %C2%B7 Samo u katalogu %C2%B7 [weights](https://huggingface.co/google/embeddinggemma-300m)

### Primjer zahtjeva

```
curl https://api.llmeu.com/v1/chat/completions \
  -H "Authorization: Bearer $LLMEU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"embeddinggemma-300m","messages":[{"role":"user","content":"Hello"}]}'
```

Za ovaj model nije postavljen playground: nijedan endpoint ga ne poslu%C5%BEuje, pa zahtjev ne bi imao kamo oti%C4%87i.

### Benchmarkovi

Nema objavljene evaluacije. To je praznina, a ne skriveni rezultat.

### Izvori

- [huggingface.co](https://huggingface.co/google/embeddinggemma-300m)
- [arxiv.org](https://arxiv.org/abs/2509.20354)

### Povijest izmjena kartice

- 17. srp 2025. %E2%80%94 Datum izdanja
- 14. lis 2026. %E2%80%94 Posljednji pregled

Posljednji pregled: 14. lis 2026.

### Zadaci

- [Dohva%C4%87anje (RAG)](/hr/tasks/rag/)