Instructions to use liodon-ai/gemma-4-12B-it-imatrix-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liodon-ai/gemma-4-12B-it-imatrix-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="liodon-ai/gemma-4-12B-it-imatrix-GGUF",
	filename="gemma4-12B-IQ2_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use liodon-ai/gemma-4-12B-it-imatrix-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 liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf liodon-ai/gemma-4-12B-it-imatrix-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 liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf liodon-ai/gemma-4-12B-it-imatrix-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 liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf liodon-ai/gemma-4-12B-it-imatrix-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 liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M

Use Docker

docker model run hf.co/liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use liodon-ai/gemma-4-12B-it-imatrix-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liodon-ai/gemma-4-12B-it-imatrix-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": "liodon-ai/gemma-4-12B-it-imatrix-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M

Ollama
How to use liodon-ai/gemma-4-12B-it-imatrix-GGUF with Ollama:
```
ollama run hf.co/liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M
```

Unsloth Studio

How to use liodon-ai/gemma-4-12B-it-imatrix-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 liodon-ai/gemma-4-12B-it-imatrix-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 liodon-ai/gemma-4-12B-it-imatrix-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for liodon-ai/gemma-4-12B-it-imatrix-GGUF to start chatting

How to use liodon-ai/gemma-4-12B-it-imatrix-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf liodon-ai/gemma-4-12B-it-imatrix-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": "liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use liodon-ai/gemma-4-12B-it-imatrix-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 liodon-ai/gemma-4-12B-it-imatrix-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 liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use liodon-ai/gemma-4-12B-it-imatrix-GGUF with Docker Model Runner:
```
docker model run hf.co/liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M
```

Lemonade

How to use liodon-ai/gemma-4-12B-it-imatrix-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-12B-it-imatrix-GGUF-Q4_K_M

List all available models

lemonade list

Gemma 4 12B IT — iMatrix GGUF (including sub-4-bit)

The only iMatrix GGUF repo for Gemma 4 12B that includes Q2 and Q3 quants.

Most iMatrix repos for this model stop at Q4. This one goes all the way down to IQ2_M (4.1 GB) — making Gemma 4 12B runnable on 6 GB VRAM with iMatrix quality.

All quants produced with llama.cpp using importance matrix calibration on a 2M token wikitext corpus.

Quick Start

Ollama

ollama run hf.co/liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M

llama.cpp

llama-cli -hf liodon-ai/gemma-4-12B-it-imatrix-GGUF:Q4_K_M

LM Studio / Jan

Search liodon-ai/gemma-4-12B-it-imatrix-GGUF and pick your quant.

Available Quants

Quant	Size	VRAM	Notes
`IQ2_M`	4.1 GB	6 GB	Ultra-tiny. iMatrix keeps it coherent where standard Q2 breaks down
`IQ3_M`	5.4 GB	7 GB	Best quality under 6 GB file size
`Q2_K`	4.5 GB	6 GB	Smallest standard quant — runs almost anywhere
`Q3_K_M`	5.7 GB	7 GB	Good balance for tight VRAM
`IQ4_XS`	6.2 GB	8 GB	iMatrix Q4 — rivals standard Q5 at smaller size
`Q4_K_M`	6.9 GB	8 GB	Recommended. Sweet spot for most setups
`Q5_K_M`	8.0 GB	10 GB	High quality
`Q6_K`	9.2 GB	12 GB	Near-lossless
`Q8_0`	12 GB	16 GB	Basically full quality

Why iMatrix Matters for Sub-4-bit Quants

Standard quantization at Q2/Q3 rounds weights uniformly — the model loses coherence, repeats itself, and produces broken output. Other iMatrix repos for this model have excluded sub-4-bit entirely for this reason.

iMatrix fixes this by identifying which weights actually matter during a calibration pass over real text, then protecting those weights from aggressive rounding. The result: IQ2_M and IQ3_M remain usable and coherent at sizes that standard Q2/Q3 can't match.

If you have 6-8 GB VRAM and want to run Gemma 4 12B, the iMatrix Q2/Q3 quants here are your only viable option for this model.

What is iMatrix?

Standard GGUF quantization: compress all weights equally → fast, but imprecise at low bit widths.

iMatrix quantization:

Run a calibration text through the full-precision model
Measure which weights activate most during inference (the "importance matrix")
Quantize with higher precision on important weights, lower precision on less important ones

Same file size. Better output. Most noticeable at Q2/Q3/Q4.

Calibration

Importance matrix computed using a 2M token sample from wikitext-103 — diverse English text covering Wikipedia articles across topics. 128 calibration chunks.

Base Model

Model: google/gemma-4-12B-it
Params: 12B
Context: 128K tokens
Architecture: Gemma 4 (multimodal)
License: Apache 2.0
Authors: Google DeepMind

Downloads last month: 332

GGUF

Model size

12B params

Architecture

gemma4

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for liodon-ai/gemma-4-12B-it-imatrix-GGUF

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Quantized

(197)

this model