Instructions to use roelfrenkema/gemma-4-E4B-it.Q8_0-med.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 roelfrenkema/gemma-4-E4B-it.Q8_0-med.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 roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf: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 roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf: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 roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_0

Use Docker

docker model run hf.co/roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_0

LM Studio
Jan
Ollama
How to use roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf with Ollama:
```
ollama run hf.co/roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_0
```
Unsloth Desktop

How to use roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_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": "roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf with Docker Model Runner:
```
docker model run hf.co/roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_0
```

Lemonade

How to use roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_0

Run and chat with the model

lemonade run user.gemma-4-E4B-it.Q8_0-med.gguf-Q8_0

List all available models

lemonade list

Hermes Agent

How to use roelfrenkema/gemma-4-E4B-it.Q8_0-med.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 roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_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 roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_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 "roelfrenkema/gemma-4-E4B-it.Q8_0-med.gguf:Q8_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"

Model Card for Model ID gemma-4-E4B-it.Q8_0-med.gguf

Gemma-4-E4B with a medical layer.

Model Details

Model Description

Gemma 4 E4B is getraind met een in het Nederlands vertaalde MedAlpaca Het is verbazingwekkend acuraat en bij uitstek geschikt voor gebruik met RAG. Ik heb ook een E2B versie beschikbaar te vinden onder

Dit is werk dat ik als vrijwilliger doe voor Impuls en Woortblind

Developed by: @roelfrenkema
Funded by [optional]: Ik zoek funding.
Model type: Gemma 4 E4B
Language(s) (NLP): NL
License: Apache
Finetuned from model [optional]: Gemma 4 E4B

Uses

Gebruik de Modelfile voor Ollama (nieuwste versie) of llama.cpp etc.

Bias, Risks, and Limitations

Disclaimer

Training Details

Training Data

training:
  max_seq_length: 2048
  num_epochs: 1
  learning_rate: 0.0001
  batch_size: 1
  gradient_accumulation_steps: 8
  warmup_steps: 100
  max_steps: -1
  save_steps: 500
  eval_steps: 0
  weight_decay: 0.001
  random_seed: 3407
  packing: false
  train_on_completions: true
  gradient_checkpointing: unsloth
  optim: adamw_8bit
  lr_scheduler_type: cosine
lora:
  lora_r: 16
  lora_alpha: 32
  lora_dropout: 0
  target_modules:
    - q_proj
    - k_proj
    - v_proj
    - o_proj
    - gate_proj
    - up_proj
    - down_proj
  use_rslora: false
  use_loftq: false
  finetune_vision_layers: true
  finetune_language_layers: true
  finetune_attention_modules: true
  finetune_mlp_modules: true

Training Procedure

UNSLOTH

Downloads last month: 42

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

8-bit

Inference Providers NEW

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