Instructions to use Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-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 Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-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 Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-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 Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-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 Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-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 Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF with Ollama:
```
ollama run hf.co/Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-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": "Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF with Docker Model Runner:
```
docker model run hf.co/Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF:Q4_K_M
```

Lemonade

How to use Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-E4B-it-SDFT_Heretic_RP-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-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 Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-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 Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-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 "Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-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"

Gemma 4 E4B it SDFT Heretic RP GGUF

This repository contains GGUF quantized files for the main merged model:

Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP

These are inference-ready GGUF artifacts for llama.cpp-compatible runtimes. The full merged Hugging Face weights are published separately in the base model repository above.

Files

gemmae4b_lr5e6_resume_r8-Q3_K_L.gguf - lower memory option.
gemmae4b_lr5e6_resume_r8-Q4_K_M.gguf - recommended default.
gemmae4b_lr5e6_resume_r8-Q5_K_M.gguf - higher quality option.
gemmae4b_lr5e6_resume_r8-Q6_K.gguf - best quality GGUF option here.
gemmae4b_lr5e6_resume_r8-mmproj-f16.gguf - shared multimodal projector file.

Notes

This is an RP-enhanced model based on the Heretic SDFT line. It is intended for research, evaluation, local RP testing, and narrative experiments.

The underlying model may have weakened safety guardrails compared with standard aligned chat models. Do not use it to generate harmful, illegal, abusive, exploitative, or otherwise unsafe content.

Suggested Starting Settings

temperature: 0.8-0.95 top_p: 0.95 top_k: 64

For most users, start with Q4_K_M. Use Q5_K_M or Q6_K if you have the memory and want better prose stability.

Downloads last month: 690

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

Inference Providers NEW

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

Model tree for Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Finetuned

Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP

Quantized

(3)

this model