Title: Gemma 4 E4B IT %E2%80%94 gemma-4-e4b-it
Canonical: https://llmeu.com/bg/models/gemma-4-e4b-it/
Markdown mirror: https://llmeu.com/bg/models/gemma-4-e4b-it.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: apache-2.0
Hosting: catalogue only %E2%80%94 not hosted on LLM EU yet
Sources: https://huggingface.co/google/gemma-4-E4B-it

# Gemma 4 E4B IT

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

%D0%9F%D0%BE%D1%81%D0%BB%D0%B5%D0%B4%D0%BD%D0%B0 %D0%BF%D1%80%D0%BE%D0%B2%D0%B5%D1%80%D0%BA%D0%B0: 14.10.2026 %D0%B3.

## %D0%A1%D1%83%D0%B2%D0%B5%D1%80%D0%B5%D0%BD%D0%B8%D1%82%D0%B5%D1%82 %D0%B8 %D1%85%D0%BE%D1%81%D1%82%D0%B8%D0%BD%D0%B3

%D0%A2%D0%BE%D0%B7%D0%B8 %D0%BC%D0%BE%D0%B4%D0%B5%D0%BB %D0%B5 %D0%B2%D0%BA%D0%BB%D1%8E%D1%87%D0%B5%D0%BD %D0%B2 %D0%BA%D0%B0%D1%82%D0%B0%D0%BB%D0%BE%D0%B3%D0%B0 %D0%B7%D0%B0 %D1%81%D0%BF%D1%80%D0%B0%D0%B2%D0%BA%D0%B0. %D0%A2%D0%BE%D0%B9 %D0%B2%D1%81%D0%B5 %D0%BE%D1%89%D0%B5 %D0%BD%D0%B5 %D1%81%D0%B5 %D1%85%D0%BE%D1%81%D1%82%D0%B2%D0%B0 %D0%B2 LLM EU %D0%B8 %D0%BD%D0%B8%D1%82%D0%BE %D0%B5%D0%B4%D0%B8%D0%BD %D1%81%D0%BE%D0%B1%D1%81%D1%82%D0%B2%D0%B5%D0%BD endpoint %D0%BD%D0%B5 %D0%B3%D0%BE %D0%BE%D0%B1%D1%81%D0%BB%D1%83%D0%B6%D0%B2%D0%B0 %D1%82%D1%83%D0%BA. %D0%97%D0%B0%D1%8F%D0%B2%D0%BA%D0%B8%D1%82%D0%B5 %D0%BA%D1%8A%D0%BC %D0%BD%D0%B5%D0%B3%D0%BE %D0%BE%D1%82%D0%B8%D0%B2%D0%B0%D1%82 %D0%B4%D0%B8%D1%80%D0%B5%D0%BA%D1%82%D0%BD%D0%BE %D0%BF%D1%80%D0%B8 %D0%B4%D0%BE%D1%81%D1%82%D0%B0%D0%B2%D1%87%D0%B8%D0%BA%D0%B0, %D0%BF%D1%80%D0%B8 %D0%BD%D0%B5%D0%B3%D0%BE%D0%B2%D0%B8%D1%82%D0%B5 %D1%81%D0%BE%D0%B1%D1%81%D1%82%D0%B2%D0%B5%D0%BD%D0%B8 %D1%83%D1%81%D0%BB%D0%BE%D0%B2%D0%B8%D1%8F.

## %D0%9E%D0%B1%D0%BE%D0%B1%D1%89%D0%B5%D0%BD%D0%B8%D0%B5

Gemma 4 E4B IT %D0%B5 %D0%BD%D0%B0%D0%B9-%D0%BC%D0%B0%D0%BB%D0%BA%D0%B8%D1%8F%D1%82 %D0%BC%D0%BE%D0%B4%D0%B5%D0%BB Gemma 4 %D1%81 %D0%B2%D0%B3%D1%80%D0%B0%D0%B4%D0%B5%D0%BD%D0%BE %D0%B0%D1%83%D0%B4%D0%B8%D0%BE, %D0%BE%D0%B1%D1%80%D0%B0%D0%B1%D0%BE%D1%82%D0%B2%D0%B0%D1%89 %D1%82%D0%B5%D0%BA%D1%81%D1%82, %D0%B8%D0%B7%D0%BE%D0%B1%D1%80%D0%B0%D0%B6%D0%B5%D0%BD%D0%B8%D1%8F %D0%B8 %D0%B0%D1%83%D0%B4%D0%B8%D0%BE %D0%B2%D1%85%D0%BE%D0%B4 %D1%81 %D0%BF%D1%80%D0%BE%D0%B7%D0%BE%D1%80%D0%B5%D1%86 %D0%BD%D0%B0 %D0%BA%D0%BE%D0%BD%D1%82%D0%B5%D0%BA%D1%81%D1%82 %D0%BE%D1%82 128K %D1%82%D0%BE%D0%BA%D0%B5%D0%BD%D0%B0. Google %D0%B7%D0%B0%D1%8F%D0%B2%D1%8F%D0%B2%D0%B0, %D1%87%D0%B5 %E2%80%9EE%E2%80%9C %D0%B2 E2B %D0%B8 E4B %D0%BE%D0%B7%D0%BD%D0%B0%D1%87%D0%B0%D0%B2%D0%B0 %D0%B5%D1%84%D0%B5%D0%BA%D1%82%D0%B8%D0%B2%D0%BD%D0%B8 %D0%BF%D0%B0%D1%80%D0%B0%D0%BC%D0%B5%D1%82%D1%80%D0%B8 %D0%B8 %D1%87%D0%B5 %D1%82%D0%B5%D0%B7%D0%B8 %D1%80%D0%B0%D0%B7%D0%BC%D0%B5%D1%80%D0%B8 %D0%B8%D0%B7%D0%BF%D0%BE%D0%BB%D0%B7%D0%B2%D0%B0%D1%82 %D0%B2%D0%B3%D1%80%D0%B0%D0%B6%D0%B4%D0%B0%D0%BD%D0%B8%D1%8F %D0%BD%D0%B0 %D1%81%D0%BB%D0%BE%D0%B9 (Per-Layer Embeddings), %D1%82%D0%B0%D0%BA%D0%B0 %D1%87%D0%B5 %D1%81%D1%8A%D1%85%D1%80%D0%B0%D0%BD%D1%8F%D0%B2%D0%B0%D0%BD%D0%B8%D1%8F%D1%82 %D0%BC%D0%BE%D0%B4%D0%B5%D0%BB %D0%B5 %D0%BE%D0%BA%D0%BE%D0%BB%D0%BE 8B %D0%BF%D0%B0%D1%80%D0%B0%D0%BC%D0%B5%D1%82%D1%80%D0%B8, %D0%B4%D0%BE%D0%BA%D0%B0%D1%82%D0%BE %D0%B5%D1%84%D0%B5%D0%BA%D1%82%D0%B8%D0%B2%D0%BD%D0%B8%D1%8F%D1%82 %D0%B1%D1%80%D0%BE%D0%B9 %D0%B5 %D0%BF%D0%BE-%D0%BC%D0%B0%D0%BB%D1%8A%D0%BA. %D0%9A%D0%B0%D1%80%D1%82%D0%B0%D1%82%D0%B0 %D0%BD%D0%B0 %D0%BC%D0%BE%D0%B4%D0%B5%D0%BB%D0%B0 %D0%BE%D1%82%D1%87%D0%B8%D1%82%D0%B0 69.4% %D0%BD%D0%B0 MMLU Pro %D0%B8 58.6% %D0%BD%D0%B0 GPQA Diamond %D0%B8 %D0%B5 %D0%BB%D0%B8%D1%86%D0%B5%D0%BD%D0%B7%D0%B8%D1%80%D0%B0%D0%BD %D0%BF%D0%BE%D0%B4 Apache-2.0.

## %D0%A1%D0%BF%D0%B5%D1%86%D0%B8%D1%84%D0%B8%D0%BA%D0%B0%D1%86%D0%B8%D0%B8

- %D0%94%D0%BE%D1%81%D1%82%D0%B0%D0%B2%D1%87%D0%B8%D0%BA
  Google DeepMind (US)
- %D0%9F%D1%80%D0%BE%D0%B7%D0%BE%D1%80%D0%B5%D1%86 %D0%BD%D0%B0 %D0%BA%D0%BE%D0%BD%D1%82%D0%B5%D0%BA%D1%81%D1%82%D0%B0
  131k
- %D0%9F%D0%B0%D1%80%D0%B0%D0%BC%D0%B5%D1%82%D1%80%D0%B8
  8B
- %D0%9C%D0%BE%D0%B4%D0%B0%D0%BB%D0%BD%D0%BE%D1%81%D1%82%D0%B8
  text, vision, audio
- %D0%9B%D0%B8%D1%86%D0%B5%D0%BD%D0%B7
  apache-2.0 %C2%B7 [licence](https://ai.google.dev/gemma/docs/gemma_4_license)
- %D0%9E%D1%82%D0%B2%D0%BE%D1%80%D0%B5%D0%BD%D0%B8 %D1%82%D0%B5%D0%B3%D0%BB%D0%B0
  yes
- %D0%94%D0%B0%D1%82%D0%B0 %D0%BD%D0%B0 %D0%B8%D0%B7%D0%B4%D0%B0%D0%B2%D0%B0%D0%BD%D0%B5
  02.03.2026 %D0%B3.
- %D0%97%D0%B0%D0%B4%D0%B0%D1%87%D0%B8
  [%D0%9D%D0%B8%D1%81%D0%BA%D0%B0 %D1%86%D0%B5%D0%BD%D0%B0](/bg/tasks/cheap/), [%D0%92%D0%B8%D0%B7%D0%B8%D1%8F](/bg/tasks/vision/), [%D0%9C%D0%BD%D0%BE%D0%B3%D0%BE%D0%B5%D0%B7%D0%B8%D1%87%D0%BD%D0%B0 %D0%BF%D0%BE%D0%B4%D0%B4%D1%80%D1%8A%D0%B6%D0%BA%D0%B0](/bg/tasks/multilingual-support/), [%D0%9E%D0%B1%D0%BE%D0%B1%D1%89%D0%B0%D0%B2%D0%B0%D0%BD%D0%B5](/bg/tasks/summarization/)

## %D0%95%D0%B7%D0%B8%D1%86%D0%B8

**%D0%A1%D0%B8%D0%BB%D0%BD%D0%BE:** en, de, fr, es, it, pt

**%D0%94%D0%BE%D1%81%D1%82%D0%B0%D1%82%D1%8A%D1%87%D0%BD%D0%BE:** nl, pl, sv, cs, ro, el, uk, ru, ar, hi, zh, ja, ko, tr

#### %D0%A1%D0%B8%D0%BB%D0%BD%D0%BE

- en
- de
- fr
- es
- it
- pt

#### %D0%94%D0%BE%D1%81%D1%82%D0%B0%D1%82%D1%8A%D1%87%D0%BD%D0%BE

- nl
- pl
- sv
- cs
- ro
- el
- uk
- ru
- ar
- hi
- zh
- ja
- ko
- tr

%D0%9D%D0%B5%D0%BF%D1%80%D0%BE%D0%B2%D0%B5%D1%80%D0%B5%D0%BD%D0%BE: %D0%B4%D0%BE%D1%81%D1%82%D0%B0%D0%B2%D1%87%D0%B8%D0%BA%D1%8A%D1%82 %D0%BD%D0%B5 %D0%B5 %D0%B4%D0%BE%D0%BA%D1%83%D0%BC%D0%B5%D0%BD%D1%82%D0%B8%D1%80%D0%B0%D0%BB %D1%82%D0%BE%D0%B2%D0%B0 %D1%82%D0%B2%D1%8A%D1%80%D0%B4%D0%B5%D0%BD%D0%B8%D0%B5. %E2%80%94 a language is listed as strong only where a source claims it; the card links the evidence where one exists.

## %D0%9A%D0%BE%D0%B3%D0%B0 %D0%B4%D0%B0 %D1%81%D0%B5 %D0%B8%D0%B7%D0%BF%D0%BE%D0%BB%D0%B7%D0%B2%D0%B0

#### %D0%A1%D0%B8%D0%BB%D0%BD%D0%B8 %D1%81%D1%82%D1%80%D0%B0%D0%BD%D0%B8

- native audio input in the small-model class
- Apache-2.0 licence
- runs on modest hardware
- text, image and audio in one checkpoint

#### %D0%9E%D0%B3%D1%80%D0%B0%D0%BD%D0%B8%D1%87%D0%B5%D0%BD%D0%B8%D1%8F

- reasoning scores well below the larger Gemma 4 sizes
- 128K-token window, half of the medium models
- no evaluation has been run by LLM EU

## %D0%A7%D0%B5%D1%81%D1%82%D0%BE %D0%B7%D0%B0%D0%B4%D0%B0%D0%B2%D0%B0%D0%BD%D0%B8 %D0%B2%D1%8A%D0%BF%D1%80%D0%BE%D1%81%D0%B8

### Is Gemma 4 E4B IT 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 Gemma 4 E4B IT released?

Gemma 4 E4B IT is recorded under apache-2.0. The recorded licence text is https://ai.google.dev/gemma/docs/gemma_4_license. 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 Gemma 4 E4B IT, and what context window does it have?

Gemma 4 E4B IT is recorded at about 8B stored (safetensors total 7,996,156,490); the card states that "E" in E2B and E4B stands for effective parameters, using Per-Layer Embeddings (source: https://huggingface.co/api/models/google/gemma-4-E4B-it), with a context window of 131072 tokens (source: https://huggingface.co/google/gemma-4-E4B-it).

### %D0%A6%D0%B5%D0%BD%D0%BE%D0%BE%D0%B1%D1%80%D0%B0%D0%B7%D1%83%D0%B2%D0%B0%D0%BD%D0%B5

%D0%A2%D0%BE%D0%B7%D0%B8 %D0%BC%D0%BE%D0%B4%D0%B5%D0%BB %D0%B5 %D0%B2%D0%BA%D0%BB%D1%8E%D1%87%D0%B5%D0%BD %D0%B2 %D0%BA%D0%B0%D1%82%D0%B0%D0%BB%D0%BE%D0%B3%D0%B0 %D0%B7%D0%B0 %D1%81%D0%BF%D1%80%D0%B0%D0%B2%D0%BA%D0%B0. %D0%A2%D0%BE%D0%B9 %D0%B2%D1%81%D0%B5 %D0%BE%D1%89%D0%B5 %D0%BD%D0%B5 %D1%81%D0%B5 %D1%85%D0%BE%D1%81%D1%82%D0%B2%D0%B0 %D0%B2 LLM EU %D0%B8 %D0%BD%D0%B8%D1%82%D0%BE %D0%B5%D0%B4%D0%B8%D0%BD %D1%81%D0%BE%D0%B1%D1%81%D1%82%D0%B2%D0%B5%D0%BD endpoint %D0%BD%D0%B5 %D0%B3%D0%BE %D0%BE%D0%B1%D1%81%D0%BB%D1%83%D0%B6%D0%B2%D0%B0 %D1%82%D1%83%D0%BA. %D0%97%D0%B0%D1%8F%D0%B2%D0%BA%D0%B8%D1%82%D0%B5 %D0%BA%D1%8A%D0%BC %D0%BD%D0%B5%D0%B3%D0%BE %D0%BE%D1%82%D0%B8%D0%B2%D0%B0%D1%82 %D0%B4%D0%B8%D1%80%D0%B5%D0%BA%D1%82%D0%BD%D0%BE %D0%BF%D1%80%D0%B8 %D0%B4%D0%BE%D1%81%D1%82%D0%B0%D0%B2%D1%87%D0%B8%D0%BA%D0%B0, %D0%BF%D1%80%D0%B8 %D0%BD%D0%B5%D0%B3%D0%BE%D0%B2%D0%B8%D1%82%D0%B5 %D1%81%D0%BE%D0%B1%D1%81%D1%82%D0%B2%D0%B5%D0%BD%D0%B8 %D1%83%D1%81%D0%BB%D0%BE%D0%B2%D0%B8%D1%8F.

### %D0%A1%D1%82%D0%B0%D1%82%D1%83%D1%81 %D0%BD%D0%B0 %D0%BF%D1%80%D0%BE%D0%B2%D0%B5%D1%80%D0%BA%D0%B0

%D0%9A%D0%BE%D0%B3%D0%B0%D1%82%D0%BE %D0%B4%D0%B0%D0%B4%D0%B5%D0%BD%D0%BE %D0%BF%D0%BE%D0%BB%D0%B5 %D0%BD%D1%8F%D0%BC%D0%B0 %D0%B8%D0%B7%D1%82%D0%BE%D1%87%D0%BD%D0%B8%D0%BA, %D0%BA%D0%B0%D1%80%D1%82%D0%B0%D1%82%D0%B0 %D0%B3%D0%BE %D0%BF%D0%BE%D0%BA%D0%B0%D0%B7%D0%B2%D0%B0 %D0%BA%D0%B0%D1%82%D0%BE %D0%BD%D0%B5%D0%BF%D1%80%D0%BE%D0%B2%D0%B5%D1%80%D0%B5%D0%BD%D0%BE, %D0%B2%D0%BC%D0%B5%D1%81%D1%82%D0%BE %D0%B4%D0%B0 %D0%B3%D0%BE %D0%BF%D0%BE%D0%BF%D1%8A%D0%BB%D0%B2%D0%B0. %D0%9F%D1%80%D0%B0%D0%B7%D0%BD%D0%BE%D1%82%D0%BE %D0%BF%D0%BE%D0%BB%D0%B5 %D0%B5 %D0%B8%D0%BD%D1%84%D0%BE%D1%80%D0%BC%D0%B0%D1%86%D0%B8%D1%8F.

LLM EU Verified %D0%BE%D0%B7%D0%BD%D0%B0%D1%87%D0%B0%D0%B2%D0%B0 %D0%B4%D0%BE%D0%BA%D1%83%D0%BC%D0%B5%D0%BD%D1%82%D0%B8%D1%80%D0%B0%D0%BD%D0%BE, %D0%B0 %D0%BD%D0%B5 %D0%B7%D0%B0%D0%BA%D0%BE%D0%BD%D0%BE%D0%B2%D0%BE %D1%81%D0%B5%D1%80%D1%82%D0%B8%D1%84%D0%B8%D1%86%D0%B8%D1%80%D0%B0%D0%BD%D0%BE. %D0%A2%D0%BE%D0%B2%D0%B0 %D0%BD%D0%B5 %D0%B5 %D0%BE%D1%86%D0%B5%D0%BD%D0%BA%D0%B0 %D0%B7%D0%B0 %D1%81%D1%8A%D0%BE%D1%82%D0%B2%D0%B5%D1%82%D1%81%D1%82%D0%B2%D0%B8%D0%B5 %D0%BF%D0%BE AI Act %D0%B8 LLM EU %D0%BD%D0%B5 %D0%B5 %D0%BE%D1%80%D0%B3%D0%B0%D0%BD %D0%BD%D0%B0 %D0%95%D0%A1.

### %D0%92%D0%B5%D1%80%D1%81%D0%B8%D0%B8 %D0%B8 %D0%B2%D0%B0%D1%80%D0%B8%D0%B0%D0%BD%D1%82%D0%B8

- catalogue %C2%B7 %D0%A1%D0%B0%D0%BC%D0%BE %D0%B2 %D0%BA%D0%B0%D1%82%D0%B0%D0%BB%D0%BE%D0%B3%D0%B0 %C2%B7 [weights](https://huggingface.co/google/gemma-4-E4B-it)

### %D0%9F%D1%80%D0%B8%D0%BC%D0%B5%D1%80%D0%BD%D0%B0 %D0%B7%D0%B0%D1%8F%D0%B2%D0%BA%D0%B0

```
curl https://api.llmeu.com/v1/chat/completions \
  -H "Authorization: Bearer $LLMEU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemma-4-e4b-it","messages":[{"role":"user","content":"Hello"}]}'
```

%D0%9D%D1%8F%D0%BC%D0%B0 %D0%B2%D0%BD%D0%B5%D0%B4%D1%80%D0%B5%D0%BD playground %D0%B7%D0%B0 %D1%82%D0%BE%D0%B7%D0%B8 %D0%BC%D0%BE%D0%B4%D0%B5%D0%BB: %D0%BD%D1%8F%D0%BC%D0%B0 endpoint, %D0%BA%D0%BE%D0%B9%D1%82%D0%BE %D0%B4%D0%B0 %D0%B3%D0%BE %D0%BE%D0%B1%D1%81%D0%BB%D1%83%D0%B6%D0%B2%D0%B0, %D1%82%D0%B0%D0%BA%D0%B0 %D1%87%D0%B5 %D0%B7%D0%B0%D1%8F%D0%B2%D0%BA%D0%B0%D1%82%D0%B0 %D0%BD%D1%8F%D0%BC%D0%B0 %D0%BA%D1%8A%D0%B4%D0%B5 %D0%B4%D0%B0 %D0%BE%D1%82%D0%B8%D0%B4%D0%B5.

### %D0%91%D0%B5%D0%BD%D1%87%D0%BC%D0%B0%D1%80%D0%BA%D0%BE%D0%B2%D0%B5

- MMLU Pro: **69.4% (vendor-reported)** [source](https://huggingface.co/google/gemma-4-E4B-it)
- AIME 2026, no tools: **42.5% (vendor-reported)** [source](https://huggingface.co/google/gemma-4-E4B-it)
- GPQA Diamond: **58.6% (vendor-reported)** [source](https://huggingface.co/google/gemma-4-E4B-it)

### %D0%98%D0%B7%D1%82%D0%BE%D1%87%D0%BD%D0%B8%D1%86%D0%B8

- [huggingface.co](https://huggingface.co/google/gemma-4-E4B-it)

### %D0%98%D1%81%D1%82%D0%BE%D1%80%D0%B8%D1%8F %D0%BD%D0%B0 %D0%BF%D1%80%D0%BE%D0%BC%D0%B5%D0%BD%D0%B8%D1%82%D0%B5 %D0%BD%D0%B0 %D0%BA%D0%B0%D1%80%D1%82%D0%B0%D1%82%D0%B0

- 02.03.2026 %D0%B3. %E2%80%94 %D0%94%D0%B0%D1%82%D0%B0 %D0%BD%D0%B0 %D0%B8%D0%B7%D0%B4%D0%B0%D0%B2%D0%B0%D0%BD%D0%B5
- 14.10.2026 %D0%B3. %E2%80%94 %D0%9F%D0%BE%D1%81%D0%BB%D0%B5%D0%B4%D0%BD%D0%B0 %D0%BF%D1%80%D0%BE%D0%B2%D0%B5%D1%80%D0%BA%D0%B0

%D0%9F%D0%BE%D1%81%D0%BB%D0%B5%D0%B4%D0%BD%D0%B0 %D0%BF%D1%80%D0%BE%D0%B2%D0%B5%D1%80%D0%BA%D0%B0: 14.10.2026 %D0%B3.

### %D0%97%D0%B0%D0%B4%D0%B0%D1%87%D0%B8

- [%D0%9D%D0%B8%D1%81%D0%BA%D0%B0 %D1%86%D0%B5%D0%BD%D0%B0](/bg/tasks/cheap/)