Instructions to use junwatu/resep-ID-gemma-4-E2B-it-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use junwatu/resep-ID-gemma-4-E2B-it-gguf 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 junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M

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 junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M

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 junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M

Use Docker

docker model run hf.co/junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use junwatu/resep-ID-gemma-4-E2B-it-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "junwatu/resep-ID-gemma-4-E2B-it-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "junwatu/resep-ID-gemma-4-E2B-it-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M

Ollama
How to use junwatu/resep-ID-gemma-4-E2B-it-gguf with Ollama:
```
ollama run hf.co/junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M
```
Unsloth Desktop

How to use junwatu/resep-ID-gemma-4-E2B-it-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use junwatu/resep-ID-gemma-4-E2B-it-gguf with Docker Model Runner:
```
docker model run hf.co/junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M
```

Lemonade

How to use junwatu/resep-ID-gemma-4-E2B-it-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M

Run and chat with the model

lemonade run user.resep-ID-gemma-4-E2B-it-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use junwatu/resep-ID-gemma-4-E2B-it-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use junwatu/resep-ID-gemma-4-E2B-it-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "junwatu/resep-ID-gemma-4-E2B-it-gguf:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Gemma 4 E2B — Resep Indonesia (GGUF)

GGUF quantization of junwatu/resep-ID-gemma-4-E2B-it, a fine-tune of google/gemma-4-e2b-it for Indonesian recipe generation.

This is the portable, runs-on-your-laptop version. Use it with llama.cpp, Ollama, LM Studio, or any GGUF-compatible runtime.

Quants in this repo

File	Size	Quality	Recommended for
`gemma-4-e2b-resep-id.Q4_K_M.gguf`	~3.2 GB	~96% of bf16	Default. Runs on any modern laptop with 8 GB+ RAM.
`gemma-4-e2b-resep-id.Q8_0.gguf`	~5.5 GB	~99.5% of bf16	Near-lossless. For 16+ GB RAM, when you want maximum quality without the full bf16 download.

Note: This model has an unusually large 250K-token vocab (Gemma 4 family), so all GGUF sizes carry a ~430 MB embedding overhead. The Q4_K_M↔Q5_K_M gap is only ~600 MB, so Q5 was skipped — jump to Q8_0 if you want noticeably better quality.

Quick start

LM Studio

Search for junwatu/resep-ID-gemma-4-E2B-it-gguf in the model browser
Download Q4_K_M
Important: in the inference settings, set Repeat penalty no_repeat_ngram_size = 6 — without this, the model can get stuck in repetition loops on long recipes

Ollama

# Pull the GGUF (if you've added it to Ollama via Modelfile)
ollama run junwatu/gemma-4-e2b-resep-id

# Or use a custom Modelfile pointing at the .gguf file:
cat > Modelfile <<EOF
FROM ./gemma-4-e2b-resep-id.Q4_K_M.gguf
PARAMETER repeat_penalty 1.05
# Note: Ollama doesn't expose no_repeat_ngram_size yet — for best quality,
# use llama.cpp directly or LM Studio.
EOF
ollama create gemma-4-e2b-resep-id -f Modelfile

llama.cpp (best — supports `--no-repeat-ngram-size`)

./llama-cli \
  -m gemma-4-e2b-resep-id.Q4_K_M.gguf \
  --no-repeat-ngram-size 6 \
  --repeat-penalty 1.05 \
  -p "Tulis resep masakan Indonesia berjudul: \"Tumis Kangkung Tempe\".
Format jawaban:
Bahan:
- (daftar bahan, satu per baris)

Langkah:
1. (langkah pertama)
2. (langkah kedua)
...
Gunakan Bahasa Indonesia."

What this model does

Give it an Indonesian recipe title, get back a structured Bahan: ... Langkah: ... recipe in natural Bahasa Indonesia. Trained on ~66K real home-cook recipes.

See the base model card for full details on what it does well, what it doesn't, and the rubric eval results vs stock Gemma 4.

⚠️ One critical inference setting

no_repeat_ngram_size = 6. Without it, the model can fall into repetition loops on long recipes (like rendang or tengkleng with many spices). With it, generations terminate cleanly.

Quality vs the bf16 original

Q4_K_M typically loses ~3-5% quality vs the full-precision model. For recipe generation that's largely imperceptible — same dish identity, same format, same step coherence. The full bf16 original lives at junwatu/resep-ID-gemma-4-E2B-it if you need maximum quality.

License

Inherits the Gemma Terms of Use from google/gemma-4-e2b-it.

Downloads last month: 2

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

4-bit

8-bit

Model tree for junwatu/resep-ID-gemma-4-E2B-it-gguf

Base model

junwatu/resep-ID-gemma-4-E2B-it

Quantized

(1)

this model

junwatu
/

resep-ID-gemma-4-E2B-it-gguf

You need to agree to share your contact information to access this model

Gemma 4 E2B — Resep Indonesia (GGUF)

Quants in this repo

Quick start

LM Studio

Ollama

llama.cpp (best — supports `--no-repeat-ngram-size`)

What this model does

⚠️ One critical inference setting

Quality vs the bf16 original

License

Model tree for junwatu/resep-ID-gemma-4-E2B-it-gguf

Dataset used to train junwatu/resep-ID-gemma-4-E2B-it-gguf

Space using junwatu/resep-ID-gemma-4-E2B-it-gguf 1

You need to agree to share your contact information to access this model

Gemma 4 E2B — Resep Indonesia (GGUF)

Quants in this repo

Quick start

LM Studio

Ollama

llama.cpp (best — supports --no-repeat-ngram-size)

What this model does

⚠️ One critical inference setting

Quality vs the bf16 original

License

Model tree for junwatu/resep-ID-gemma-4-E2B-it-gguf

Dataset used to train junwatu/resep-ID-gemma-4-E2B-it-gguf

Space using junwatu/resep-ID-gemma-4-E2B-it-gguf 1

llama.cpp (best — supports `--no-repeat-ngram-size`)