Instructions to use ManniX-ITA/gemma-4-A4B-109e-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ManniX-ITA/gemma-4-A4B-109e-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ManniX-ITA/gemma-4-A4B-109e-it-GGUF",
	filename="gemma-4-A4B-109e-it-CD-Q3_K_M.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 ManniX-ITA/gemma-4-A4B-109e-it-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ManniX-ITA/gemma-4-A4B-109e-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ManniX-ITA/gemma-4-A4B-109e-it-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 ManniX-ITA/gemma-4-A4B-109e-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ManniX-ITA/gemma-4-A4B-109e-it-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 ManniX-ITA/gemma-4-A4B-109e-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ManniX-ITA/gemma-4-A4B-109e-it-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 ManniX-ITA/gemma-4-A4B-109e-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ManniX-ITA/gemma-4-A4B-109e-it-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ManniX-ITA/gemma-4-A4B-109e-it-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use ManniX-ITA/gemma-4-A4B-109e-it-GGUF with Ollama:
```
ollama run hf.co/ManniX-ITA/gemma-4-A4B-109e-it-GGUF:Q4_K_M
```

Unsloth Studio

How to use ManniX-ITA/gemma-4-A4B-109e-it-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 ManniX-ITA/gemma-4-A4B-109e-it-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 ManniX-ITA/gemma-4-A4B-109e-it-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ManniX-ITA/gemma-4-A4B-109e-it-GGUF to start chatting

How to use ManniX-ITA/gemma-4-A4B-109e-it-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ManniX-ITA/gemma-4-A4B-109e-it-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": "ManniX-ITA/gemma-4-A4B-109e-it-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ManniX-ITA/gemma-4-A4B-109e-it-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 ManniX-ITA/gemma-4-A4B-109e-it-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 ManniX-ITA/gemma-4-A4B-109e-it-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use ManniX-ITA/gemma-4-A4B-109e-it-GGUF with Docker Model Runner:
```
docker model run hf.co/ManniX-ITA/gemma-4-A4B-109e-it-GGUF:Q4_K_M
```

Lemonade

How to use ManniX-ITA/gemma-4-A4B-109e-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ManniX-ITA/gemma-4-A4B-109e-it-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-A4B-109e-it-GGUF-Q4_K_M

List all available models

lemonade list

gemma-4-A4B-109e-it-GGUF

GGUF quantizations of ManniX-ITA/gemma-4-A4B-109e-it — an expert-pruned Gemma 4 26B-A4B (128 to 109 experts, 26B to 22.4B params).

All standard quants made using imatrix with calibration data v5.

ContribDynamic (CD) Quants

CD quants use per-layer dynamic quantization based on actual expert contribution analysis of the model. Important layers (early layers that contribute more to the residual stream) get higher precision, while less important layers get lower precision.

For a CD-Q4_K_M target:

Layer 0 (highest importance): Q5_K precision
Layers 1-6, 10 (medium importance): Q4_K precision
Layers 7-29 (lower importance): Q3_K precision
Output/embeddings: Q8_0 precision

This approach is inspired by Unsloth's UD quantization but uses our own expert contribution profiling data derived from measuring actual norms across 40 calibration prompts.

Available Quantizations

Quantization	Size
Q8_0	21.65 GB
Q6_K_L	18.40 GB
Q6_K	18.23 GB
Q5_K_L	15.59 GB
Q5_K_M	15.42 GB
Q5_K_S	14.51 GB
Q4_K_L	13.71 GB
Q4_K_M	13.54 GB
Q4_1	12.89 GB
Q4_K_S	12.48 GB
Q4_0	11.67 GB
IQ4_NL	11.67 GB
IQ4_XS	11.25 GB
Q3_K_XL	10.90 GB
IQ3_M	10.03 GB
Q3_K_L	11.18 GB
Q3_K_M	10.74 GB
Q3_K_S	9.88 GB
IQ3_XS	9.41 GB
IQ3_XXS	9.14 GB
Q2_K	8.57 GB
IQ2_M	8.39 GB
IQ2_S	7.99 GB
IQ2_XS	7.94 GB
IQ2_XXS	7.52 GB
CD-Q6_K	15.80 GB
CD-Q5_K_M	13.51 GB
CD-Q4_K_M	11.08 GB
CD-Q3_K_M	10.37 GB

All quants passed a 3-question sanity check (capital cities in JSON format) via llama.cpp before upload.

How to Use

Original Model

See ManniX-ITA/gemma-4-A4B-109e-it for the full model card, pruning methodology, and benchmark results (71.7% GPQA Diamond).

License

Gemma license

Downloads last month: 176

GGUF

Model size

22B params

Architecture

gemma4

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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

Model tree for ManniX-ITA/gemma-4-A4B-109e-it-GGUF

Base model

google/gemma-4-26B-A4B

Finetuned

google/gemma-4-26B-A4B-it

Finetuned

ManniX-ITA/gemma-4-A4B-109e-it

Quantized

(1)

this model