gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs

Instructions to use CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs")
config = load_config("CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

llama-cpp-python

How to use CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs",
	filename="GGUFs/GemmaDeckardThinking-Q4_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K
# Run inference directly in the terminal:
llama-cli -hf CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K
# Run inference directly in the terminal:
llama-cli -hf CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K

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 CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K

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 CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K

Use Docker

docker model run hf.co/CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K

LM Studio
Jan

vLLM

How to use CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K

Ollama
How to use CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs with Ollama:
```
ollama run hf.co/CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K
```

Unsloth Studio new

How to use CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs 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 CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs 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 CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs to start chatting

Pi new

How to use CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs"

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 CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs

Run Hermes

hermes

Docker Model Runner
How to use CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs with Docker Model Runner:
```
docker model run hf.co/CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K
```

Lemonade

How to use CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs:Q6_K

Run and chat with the model

lemonade run user.gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs-Q6_K

List all available models

lemonade list

gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUF

This is a Deckard(qx) experimental quant.

Brainwaves

         arc   arc/e boolq hswag obkqa piqa  wino
qx86-hi  0.431,0.505,0.426,0.670,0.376,0.766,0.710

Base model

gemma-4-31B-it (Instruct)
qx86-hi  0.496,0.653,0.901,0.624,0.380,0.732,0.653

Previous model

gemma-3-27b-it-heretic
q8       0.557,0.711,0.868,0.533,0.452,0.706,0.695

As I don't have an easy way to test this until LMStudio supports it, please Like it only if you had a good experience.

Thank you,

-G

Downloads last month: 2,537

Safetensors

Model size

8B params

Tensor type

BF16

U32

MLX

Hardware compatibility

8-bit

Model tree for CountCandy/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUFs

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Finetuned

DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking

Quantized

(10)

this model