Instructions to use thepytales/gemma-4-e4b-lora-edition with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use thepytales/gemma-4-e4b-lora-edition 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 thepytales/gemma-4-e4b-lora-edition:Q4_0
# Run inference directly in the terminal:
llama cli -hf thepytales/gemma-4-e4b-lora-edition:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf thepytales/gemma-4-e4b-lora-edition:Q4_0
# Run inference directly in the terminal:
llama cli -hf thepytales/gemma-4-e4b-lora-edition:Q4_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf thepytales/gemma-4-e4b-lora-edition:Q4_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf thepytales/gemma-4-e4b-lora-edition:Q4_0

Use Docker

docker model run hf.co/thepytales/gemma-4-e4b-lora-edition:Q4_0

Llama new
LM Studio
Jan
Ollama
How to use thepytales/gemma-4-e4b-lora-edition with Ollama:
```
ollama run hf.co/thepytales/gemma-4-e4b-lora-edition:Q4_0
```
Unsloth Desktop

How to use thepytales/gemma-4-e4b-lora-edition with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf thepytales/gemma-4-e4b-lora-edition:Q4_0

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": "thepytales/gemma-4-e4b-lora-edition:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use thepytales/gemma-4-e4b-lora-edition with Docker Model Runner:
```
docker model run hf.co/thepytales/gemma-4-e4b-lora-edition:Q4_0
```

Lemonade

How to use thepytales/gemma-4-e4b-lora-edition with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull thepytales/gemma-4-e4b-lora-edition:Q4_0

Run and chat with the model

lemonade run user.gemma-4-e4b-lora-edition-Q4_0

List all available models

lemonade list

Hermes Agent

How to use thepytales/gemma-4-e4b-lora-edition with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf thepytales/gemma-4-e4b-lora-edition:Q4_0

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 thepytales/gemma-4-e4b-lora-edition:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use thepytales/gemma-4-e4b-lora-edition with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf thepytales/gemma-4-e4b-lora-edition:Q4_0

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 "thepytales/gemma-4-e4b-lora-edition:Q4_0" \
  --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"

Gemma 4 E4B – Lora Edition

Gewichte unverändert, von uns ausgewählt, gemessen und für Lora eingestellt.


Basismodell	google/gemma-4-E4B-it
Urheber	Google DeepMind
Lizenz	Apache-2.0 – Gemma-4-Lizenzhinweise von Google: https://ai.google.dev/gemma/docs/gemma_4_license – Lizenztext liegt bei (`LICENSE`)
Bereitgestellt von	PyTales für die App Lora

Dateien

Teil	Datei	Größe	SHA-256	Quelle (fester Stand)
Gemma 4 E4B – Lora Edition	`gemma-4-E4B-it-Q4_0.gguf`	4.59 GB	`a555b900214b477d8880e7832e0b8925e139b0159640036b09fe472b6f2097f2`	ggml-org/gemma-4-E4B-it-GGUF @ `a69f018`
Gemma 4 E4B Bildteil – Lora Edition	`mmproj-gemma-4-E4B-it-Q8_0.gguf`	559.9 MB	`197f49a93027f9843772bd24a6a9e0be2a32a788de5a3def330e9c585d86edd1`	ggml-org/gemma-4-E4B-it-GGUF @ `a69f018`

Was „Lora Edition“ heißt

Wir haben das Modell für die App Lora ausgewählt, auf unseren Geräten gemessen und für Lora eingestellt (Kontext, Vorlage). Die Dateien sind byte-gleich mit der genannten Quelle – die SHA-256-Werte oben lassen sich nachprüfen. Basismodell, Urheber und Lizenz bleiben wie im Original. Die Urheber haben diese Ausgabe weder geprüft noch gebilligt; für die Nutzung gilt allein die Lizenz des Originals.

Downloads last month: -

GGUF

Model size

7B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for thepytales/gemma-4-e4b-lora-edition

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(450)

this model