Instructions to use macwhisperer/Gemma4-26B-SuperMoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use macwhisperer/Gemma4-26B-SuperMoE 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 macwhisperer/Gemma4-26B-SuperMoE:Q4_0
# Run inference directly in the terminal:
llama cli -hf macwhisperer/Gemma4-26B-SuperMoE:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf macwhisperer/Gemma4-26B-SuperMoE:Q4_0
# Run inference directly in the terminal:
llama cli -hf macwhisperer/Gemma4-26B-SuperMoE:Q4_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 macwhisperer/Gemma4-26B-SuperMoE:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf macwhisperer/Gemma4-26B-SuperMoE:Q4_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 macwhisperer/Gemma4-26B-SuperMoE:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf macwhisperer/Gemma4-26B-SuperMoE:Q4_0

Use Docker

docker model run hf.co/macwhisperer/Gemma4-26B-SuperMoE:Q4_0

LM Studio
Jan
Ollama
How to use macwhisperer/Gemma4-26B-SuperMoE with Ollama:
```
ollama run hf.co/macwhisperer/Gemma4-26B-SuperMoE:Q4_0
```
Unsloth Desktop

How to use macwhisperer/Gemma4-26B-SuperMoE with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf macwhisperer/Gemma4-26B-SuperMoE: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": "macwhisperer/Gemma4-26B-SuperMoE:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use macwhisperer/Gemma4-26B-SuperMoE with Docker Model Runner:
```
docker model run hf.co/macwhisperer/Gemma4-26B-SuperMoE:Q4_0
```

Lemonade

How to use macwhisperer/Gemma4-26B-SuperMoE with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull macwhisperer/Gemma4-26B-SuperMoE:Q4_0

Run and chat with the model

lemonade run user.Gemma4-26B-SuperMoE-Q4_0

List all available models

lemonade list

Hermes Agent

How to use macwhisperer/Gemma4-26B-SuperMoE with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf macwhisperer/Gemma4-26B-SuperMoE: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 macwhisperer/Gemma4-26B-SuperMoE:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use macwhisperer/Gemma4-26B-SuperMoE with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf macwhisperer/Gemma4-26B-SuperMoE: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 "macwhisperer/Gemma4-26B-SuperMoE: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"

📟 Gemma4-26B-MoE-iMatrix-QAT-Q4_0.gguf (2026 Edition)

"Local intelligence... to the max."

This is a custom-quantized version of Gemma4-26B-QAT, specifically optimized to obtain the highest possible local byte-intelligence ratio with 24GB+ RAM consumer laptops or computers.

🧠 Why this model is different

Unlike a standard quant, this model was processed using a custom Importance Matrix (imatrix). The training data for the imatrix was hand-curated to preserve:

Incredible reasoning: Inclusion of custom coding examples built with frontier models provides high retention of very specific and sharp architectural reasoning skills
Logical Flow: Inclusion of llama.cpp source code, logic puzzles, and historical writing in the imatrix training to ensure the model stays coherent at low bitrates.
High Speed: Built using llama.cpp specifically for local-first AI and edge computing setups like apple silicon with minimum 24GB RAM

🛠 Quantization Details

Base Model: Gemma4-26B-QAT
Quantization: Q4_0
Format: GGUF
Size: ~14.49 GB
Context Length: 262144 tokens

⚙️ Recommended Inference Settings

Optimize for balance between creativity and coherence:

--repeat-penalty: 1.1 – 1.4 (Sweet spot! Pushes away from familiar loops. >1.5 causes "robot-speak".)
--repeat-last-n: 128 – 256 (Larger window ensures the model doesn't forget recent repetitions.)
--temperature: 0.7 – 0.8 (Prevents over-committing to safe/repetitive tokens.)
--top-p: 0.90 (Trims low-probability hallucinations without killing creativity.)
--min-p: 0.05 – 0.1 (Optional: Prunes very low-probability tokens if your backend supports it.)