Instructions to use blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF",
	filename="Gemma-4-14B-A4B-F16.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 blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf blascotobasco/Gemma-4-14B-A4B-Heretic-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 blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf blascotobasco/Gemma-4-14B-A4B-Heretic-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 blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M

Use Docker

docker model run hf.co/blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF with Ollama:
```
ollama run hf.co/blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M
```

Unsloth Studio

How to use blascotobasco/Gemma-4-14B-A4B-Heretic-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 blascotobasco/Gemma-4-14B-A4B-Heretic-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 blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF to start chatting

How to use blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M

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": "blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf blascotobasco/Gemma-4-14B-A4B-Heretic-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 blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF with Docker Model Runner:
```
docker model run hf.co/blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M
```

Lemonade

How to use blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull blascotobasco/Gemma-4-14B-A4B-Heretic-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-14B-A4B-Heretic-GGUF-Q4_K_M

List all available models

lemonade list

Following on my experiments with restoring pruned models, this is Gemma 4 26B A4B pruned down from 128 to 64 experts with a significantly more effective pruning strategy than the previous attempt, and then given GaLore based full parameter training on only the LIMO and LIMA datasets.

The model has proven to be remarkably resilient to pruning, and while it failed in most complex tasks post prune, the training has repaired its ability to roleplay, follow instructions and logical reasoning. However a major caveat of this training run being so short is that the model struggles heavily in math. Asking a complex arithmetic question may cause gibberish or otherwise nonsensical output at worst, and the model being incorrect or giving up at best.

However the model was rigorously tested on both roleplaying and mathematics at the same time within one prompt, and while it struggles with math aside from basic calculations, it is exceptional at staying in character.

This model should be much higher quality than my previous attempt, but do not rely on it for complex tasks as a pruned model is always susceptible to errors.

The prune was based on a Heretic abliterated version of Gemma 4 26B A4B IT.