Instructions to use Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW",
	filename="gemma-4-26B-A4B-it-q6k-q5k_ffn.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 Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16
# Run inference directly in the terminal:
llama-cli -hf Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16
# Run inference directly in the terminal:
llama-cli -hf Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16

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 Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16
# Run inference directly in the terminal:
./llama-cli -hf Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16

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 Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16

Use Docker

docker model run hf.co/Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16

LM Studio
Jan
Ollama
How to use Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW with Ollama:
```
ollama run hf.co/Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16
```

Unsloth Studio

How to use Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW 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 Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW 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 Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW to start chatting

How to use Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16

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": "Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16

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 Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW with Docker Model Runner:
```
docker model run hf.co/Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16
```

Lemonade

How to use Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW:F16

Run and chat with the model

lemonade run user.gemma-4-26B-A4B-it-GGUF-6.52BPW-F16

List all available models

lemonade list

~~This is currently a STATIC quant, because the imatrix tool seems to be broken with Gemma 4 (>100 ppl). I will update with an imatrix once I can verify correctness.~~

I made a custom imatrix dataset by slapping together random columns from some popular datasets on huggingface and formatting using the official jinja template. Comapred to the unstructured bartowski dataset, PPL went from multiple thousands to single digits, so I think it should be good now. Just in case, I mirrored the old static quant to https://huggingface.co/Beinsezii/gemma-4-26B-A4B-it-GGUF-6.52BPW-static

6.52 bpw, a mixture of Q6_K, Q5_K, and Q8_0

Fits ~75k F16 CTX + MMPROJ on a 24GiB GPU, or ~150k CTX without vision. Measured on a DE, not headless.