Instructions to use timothydillan/gemma4-e2b-balinese-mt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use timothydillan/gemma4-e2b-balinese-mt with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="timothydillan/gemma4-e2b-balinese-mt",
	filename="gemma4-e2b-idban-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "\"Меня зовут Вольфганг и я живу в Берлине\""
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use timothydillan/gemma4-e2b-balinese-mt with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf timothydillan/gemma4-e2b-balinese-mt:Q8_0
# Run inference directly in the terminal:
llama cli -hf timothydillan/gemma4-e2b-balinese-mt:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf timothydillan/gemma4-e2b-balinese-mt:Q8_0
# Run inference directly in the terminal:
llama cli -hf timothydillan/gemma4-e2b-balinese-mt:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf timothydillan/gemma4-e2b-balinese-mt:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf timothydillan/gemma4-e2b-balinese-mt:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf timothydillan/gemma4-e2b-balinese-mt:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf timothydillan/gemma4-e2b-balinese-mt:Q8_0

Use Docker

docker model run hf.co/timothydillan/gemma4-e2b-balinese-mt:Q8_0

LM Studio
Jan
Ollama
How to use timothydillan/gemma4-e2b-balinese-mt with Ollama:
```
ollama run hf.co/timothydillan/gemma4-e2b-balinese-mt:Q8_0
```

Unsloth Studio

How to use timothydillan/gemma4-e2b-balinese-mt with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for timothydillan/gemma4-e2b-balinese-mt to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for timothydillan/gemma4-e2b-balinese-mt to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for timothydillan/gemma4-e2b-balinese-mt to start chatting

Atomic Chat new
Docker Model Runner
How to use timothydillan/gemma4-e2b-balinese-mt with Docker Model Runner:
```
docker model run hf.co/timothydillan/gemma4-e2b-balinese-mt:Q8_0
```

Lemonade

How to use timothydillan/gemma4-e2b-balinese-mt with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull timothydillan/gemma4-e2b-balinese-mt:Q8_0

Run and chat with the model

lemonade run user.gemma4-e2b-balinese-mt-Q8_0

List all available models

lemonade list

Gemma 4 E2B — Balinese ↔ Indonesian (v0)

A LoRA-SFT fine-tune of Gemma 4 E2B for Indonesian ↔ Balinese translation, built as part of Open Indonesia Models — open language/speech models for Indonesian regional languages, starting with Balinese.

On-device first: ships as a q8_0 GGUF (4.6 GB) runnable in Ollama / llama.cpp / LM Studio.

Results (chrF++, 100 held-out NusaX-MT pairs, greedy)

Direction	Base Gemma-4-E2B	This model (q8_0)	Δ
Indonesian → Balinese	29.33	51.88	+22.6
Balinese → Indonesian	34.46	60.93	+26.5

Fine-tuning roughly doubles chrF++. Trained on 1,200 clean NusaX-MT pairs (2 epochs, Unsloth LoRA SFT, final loss 0.328). This is a v0 translation baseline, not a general assistant — expect occasional lexical slips.

Usage (Ollama)

# Build from the GGUF (Modelfile uses Gemma-4's <|turn> template):
ollama create oim-bali -f Modelfile
ollama run oim-bali "Translate from Indonesian to Balinese.

Selamat pagi, semoga harimu menyenangkan."

Prompt format follows training: Translate from Indonesian to Balinese.\n\n<text> (or ... to Indonesian.). Register conditioning where available: Translate from Indonesian to Balinese (register=Alus Sor).\n\n<text>.

Files

gemma4-e2b-idban-Q8_0.gguf — the runnable on-device model (q8_0, PLE-safe).
adapter/ — the LoRA adapter (apply onto google/gemma-4-E2B-it).
Modelfile — Ollama Modelfile with the correct Gemma-4 chat template.

Notes

Quant: q8_0 (NOT q4_k_m). Gemma 4 E2B uses Per-Layer Embeddings (PLE) which are highly quant-sensitive; q8_0 keeps them lossless. Exported via llama.cpp convert_hf_to_gguf.py --outtype q8_0 (stock mlx-lm fails on the multimodal arch).

Attribution & license

Base: Gemma 4 (Google) — Gemma Terms of Use.
Training data: NusaX-MT (IndoNLP), CC BY-SA 4.0 — Winata et al., NusaX, EACL 2023 (arXiv:2205.15960). Redistribution of data derivatives must preserve attribution + ShareAlike.
Built for non-commercial use and open sharing.

Downloads last month: 25

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

8-bit

Model tree for timothydillan/gemma4-e2b-balinese-mt

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Quantized

(275)

this model

Paper for timothydillan/gemma4-e2b-balinese-mt

NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages

Paper • 2205.15960 • Published May 31, 2022