Instructions to use Mediform/gemma4-e4b-v13-plainlora-r16-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mediform/gemma4-e4b-v13-plainlora-r16-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Mediform/gemma4-e4b-v13-plainlora-r16-gguf",
	filename="gemma4-e4b-v13-plainlora-r16.Q4_1.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Mediform/gemma4-e4b-v13-plainlora-r16-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 Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1
# Run inference directly in the terminal:
llama cli -hf Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1
# Run inference directly in the terminal:
llama cli -hf Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1

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 Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1
# Run inference directly in the terminal:
./llama-cli -hf Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1

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 Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1

Use Docker

docker model run hf.co/Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1

LM Studio
Jan
Ollama
How to use Mediform/gemma4-e4b-v13-plainlora-r16-gguf with Ollama:
```
ollama run hf.co/Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1
```

Unsloth Studio

How to use Mediform/gemma4-e4b-v13-plainlora-r16-gguf 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 Mediform/gemma4-e4b-v13-plainlora-r16-gguf 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 Mediform/gemma4-e4b-v13-plainlora-r16-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Mediform/gemma4-e4b-v13-plainlora-r16-gguf to start chatting

How to use Mediform/gemma4-e4b-v13-plainlora-r16-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Mediform/gemma4-e4b-v13-plainlora-r16-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 Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1

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 Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Mediform/gemma4-e4b-v13-plainlora-r16-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1

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 "Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1" \
  --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"

Docker Model Runner
How to use Mediform/gemma4-e4b-v13-plainlora-r16-gguf with Docker Model Runner:
```
docker model run hf.co/Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1
```

Lemonade

How to use Mediform/gemma4-e4b-v13-plainlora-r16-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Mediform/gemma4-e4b-v13-plainlora-r16-gguf:Q4_1

Run and chat with the model

lemonade run user.gemma4-e4b-v13-plainlora-r16-gguf-Q4_1

List all available models

lemonade list

gemma4-e4b-v13-plainlora-r16 — GGUF

llama.cpp GGUF of Scribion's German medical fact-extraction model — the project champion (E4B + plain LoRA r16, no QAT, on the v13b dataset).

Files

file	what	precision
`gemma4-e4b-v13-plainlora-r16.Q4_1.gguf`	language model	Q4_1 (affine, gs32) — 5.4 GB
`mmproj-gemma4-e4b-v13-bf16.gguf`	vision + audio projector	bf16 — 0.99 GB

Both built from the QAT base the adapter was finetuned on (bf16 → Q4_1 for the LM; bf16 mmproj exported directly from that base's vision/audio towers, which the language-only LoRA leaves untouched). Use Q4_1 or Q4_K_M, never Q4_0 (the symmetric Q4_0 grid degenerates this asymmetric-QAT model).

Adapter: Mediform/gemma4-e4b-v13-plainlora-r16
MLX-swift deploy: Mediform/gemma4-e4b-v13-plainlora-r16-mlx-4bit

Q4_1 is the validated non-Apple proxy for the MLX-4bit deploy (reproduces the Mac mlx-swift eval closely). Beats the stock base on froehlich, ~on par on arztbericht.

Use

# text-only extraction
llama-server -m gemma4-e4b-v13-plainlora-r16.Q4_1.gguf -c 12288 -np 1 -ngl 99
# multimodal (image / audio input) — add the projector
llama-server -m gemma4-e4b-v13-plainlora-r16.Q4_1.gguf \
             --mmproj mmproj-gemma4-e4b-v13-bf16.gguf -c 12288 -ngl 99

Extraction prompts are multi-call (one per section type); temp 0.3.

Downloads last month: 216

GGUF

Model size

8B 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 Mediform/gemma4-e4b-v13-plainlora-r16-gguf

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Finetuned

google/gemma-4-E4B-it-qat-q4_0-unquantized

Quantized

(29)

this model