Instructions to use Ninnix96/gemma-4-26B-A4B-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 Ninnix96/gemma-4-26B-A4B-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 Ninnix96/gemma-4-26B-A4B-gguf:Q4_0
# Run inference directly in the terminal:
llama cli -hf Ninnix96/gemma-4-26B-A4B-gguf:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ninnix96/gemma-4-26B-A4B-gguf:Q4_0
# Run inference directly in the terminal:
llama cli -hf Ninnix96/gemma-4-26B-A4B-gguf:Q4_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Ninnix96/gemma-4-26B-A4B-gguf:Q4_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf Ninnix96/gemma-4-26B-A4B-gguf:Q4_0

Use Docker

docker model run hf.co/Ninnix96/gemma-4-26B-A4B-gguf:Q4_0

Llama new
LM Studio
Jan

vLLM

How to use Ninnix96/gemma-4-26B-A4B-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ninnix96/gemma-4-26B-A4B-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ninnix96/gemma-4-26B-A4B-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ninnix96/gemma-4-26B-A4B-gguf:Q4_0

Ollama
How to use Ninnix96/gemma-4-26B-A4B-gguf with Ollama:
```
ollama run hf.co/Ninnix96/gemma-4-26B-A4B-gguf:Q4_0
```
Unsloth Desktop

How to use Ninnix96/gemma-4-26B-A4B-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ninnix96/gemma-4-26B-A4B-gguf: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": "Ninnix96/gemma-4-26B-A4B-gguf:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Ninnix96/gemma-4-26B-A4B-gguf with Docker Model Runner:
```
docker model run hf.co/Ninnix96/gemma-4-26B-A4B-gguf:Q4_0
```

Lemonade

How to use Ninnix96/gemma-4-26B-A4B-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ninnix96/gemma-4-26B-A4B-gguf:Q4_0

Run and chat with the model

lemonade run user.gemma-4-26B-A4B-gguf-Q4_0

List all available models

lemonade list

Hermes Agent

How to use Ninnix96/gemma-4-26B-A4B-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 Ninnix96/gemma-4-26B-A4B-gguf: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 Ninnix96/gemma-4-26B-A4B-gguf:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Ninnix96/gemma-4-26B-A4B-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ninnix96/gemma-4-26B-A4B-gguf: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 "Ninnix96/gemma-4-26B-A4B-gguf: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"

gemma-4-26B-A4B-it — Q4 / Q3 / Q2 GGUF

Fast GGUFs for mainstream llama.cpp, quantized antirez style: routed experts quantized hard, everything else protected.

Recipe (antirez style)

Tensor group	Q4	Q3	Q2
Routed expert gate / up (fused)	Q4_K (calibrated)	IQ3_XXS (imatrix)	IQ2_XXS (imatrix)
Routed expert down	MXFP4	IQ4_NL (imatrix)	Q4_0
Shared experts, attention, output	Q8_0	Q8_0	Q8_0
Token embeddings	F16	F16	F16
Routers, norms, biases	F32	F32	F32

Same strategy as Salvatore Sanfilippo's Qwen3.8 Flash Next (Q4_K + MXFP4) and DeepSeek V4 (IQ2_XXS + Q2_K) quants. Notes: gemma's down-expert rows are 704 wide and K-quants need multiples of 256, so Q4_K/Q3_K/Q2_K are impossible there — the down path uses the best fitting alternative in each class (MXFP4, IQ4_NL, Q4_0). Imatrix: unsloth.

Files

File	Size
gemma-4-26B-A4B-it-Q4-Q4_K-MXFP4.gguf	14.80 GiB
gemma-4-26B-A4B-it-Q3-IQ3_XXS-IQ4_NL.gguf	12.48 GiB
gemma-4-26B-A4B-it-Q2-IQ2_XXS-Q4_0.gguf	10.70 GiB

Usage

# interactive chat (multimodal: add --mmproj mmproj-F16.gguf for images)
llama-cli -m gemma-4-26B-A4B-it-Q4-Q4_K-MXFP4.gguf -t 8 -c 8192

# server
llama-server -m gemma-4-26B-A4B-it-Q4-Q4_K-MXFP4.gguf -t 8 -c 32768 --host 0.0.0.0 --port 8080