Instructions to use Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF",
	filename="gemma-4-12b-it-Imatrix-IQ4_XS.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 Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-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 Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS

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 Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS

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 Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS

Use Docker

docker model run hf.co/Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS

LM Studio
Jan

vLLM

How to use Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-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": "Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS

Ollama
How to use Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF with Ollama:
```
ollama run hf.co/Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS
```

Unsloth Studio

How to use Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-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 Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-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 Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF to start chatting

How to use Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS

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": "Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-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 Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS

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 Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS

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 "Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS" \
  --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"

Docker Model Runner
How to use Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF with Docker Model Runner:
```
docker model run hf.co/Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS
```

Lemonade

How to use Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF:IQ4_XS

Run and chat with the model

lemonade run user.gemma-4-12b-it-Imatrix-IQ4_XS-GGUF-IQ4_XS

List all available models

lemonade list

Gemma 4 12B Unified — Imatrix IQ4_XS GGUF

Custom importance-matrix quantized version of google/gemma-4-12B-it, the encoder-free unified multimodal model from Gemma 4 family.

Quantization details

Base model: google/gemma-4-12B-it (BF16, ~23.8 GB)
Method: IQ4_XS with custom importance matrix calibration
Calibration dataset: reapmix_imatrix (2237 chunks)
Embedding protection: per_layer_token_embd.weight preserved in Q6_K via imatrix
Final size: 6.16 GB (4.45 BPW)
Compression ratio: 0.26x from BF16

Architecture notes

Gemma 4 12B uses the new gemma4_unified architecture — encoder-free multimodal design where vision and audio modalities are projected directly into the decoder through lightweight linear layers, rather than dedicated encoders. The model has 48 layers with shared KV in every 6th global layer (head_count_kv=1), optimizing memory footprint for the 256K context window.

This quant requires llama.cpp commit including PR #24088 or later for gemma4_unified architecture support.

Hardware benchmark

Tested on NVIDIA RTX PRO 5000 Blackwell (72 GB VRAM):

Metric	Value
Generation speed	99-104 tok/s sustained
VRAM at 32K context	~10 GB (with FlashAttention)
Time to first token	<1 s on typical prompts

Recommended sampling

Per Google's Gemma 4 best practices — deviating from these will cause repetition loops on edge-case prompts:

temperature: 1.0
top_p: 0.95
top_k: 64
repeat_penalty: 1.0 (disabled)

Thinking mode

To enable Gemma 4's reasoning mode, prepend <|think|> to the system prompt. The model will produce internal reasoning in a <|channel>thought ... <channel|> block before the final answer.

Pipeline

Built using a hybrid CPU/GPU pipeline across a homelab cluster:

BF16 to GGUF conversion on AI workstation (Dell 5820 + RTX PRO 5000)
Importance matrix computed on GPU (~60 minutes for 2237 chunks)
IQ4_XS quantization on dual Xeon E5-2699 v3 (88 threads, 128 seconds)
Inter-node transfer via 40GbE direct-attach (RoCEv2 ring)

Quick start

./llama-server \
  -m gemma-4-12b-it-Imatrix-IQ4_XS.gguf \
  -c 32768 \
  -ngl 99 \
  --host 0.0.0.0 \
  --port 8080

License

Apache 2.0 (inherited from base model).

Downloads last month: 135

GGUF

Model size

12B params

Architecture

gemma4

Hardware compatibility

4-bit

Model tree for Krasnopjorovs/gemma-4-12b-it-Imatrix-IQ4_XS-GGUF

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Quantized

(265)

this model