supergemma4-26b-uncensored-gguf-v2

Instructions to use Deepdive404/supergemma4-26b-uncensored-gguf-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Deepdive404/supergemma4-26b-uncensored-gguf-v2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Deepdive404/supergemma4-26b-uncensored-gguf-v2",
	filename="supergemma4-26b-uncensored-fast-v2-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Deepdive404/supergemma4-26b-uncensored-gguf-v2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Deepdive404/supergemma4-26b-uncensored-gguf-v2: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 Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Deepdive404/supergemma4-26b-uncensored-gguf-v2: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 Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M

Use Docker

docker model run hf.co/Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M

LM Studio
Jan

vLLM

How to use Deepdive404/supergemma4-26b-uncensored-gguf-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Deepdive404/supergemma4-26b-uncensored-gguf-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Deepdive404/supergemma4-26b-uncensored-gguf-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M

Ollama
How to use Deepdive404/supergemma4-26b-uncensored-gguf-v2 with Ollama:
```
ollama run hf.co/Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M
```

Unsloth Studio new

How to use Deepdive404/supergemma4-26b-uncensored-gguf-v2 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 Deepdive404/supergemma4-26b-uncensored-gguf-v2 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 Deepdive404/supergemma4-26b-uncensored-gguf-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Deepdive404/supergemma4-26b-uncensored-gguf-v2 to start chatting

Pi new

How to use Deepdive404/supergemma4-26b-uncensored-gguf-v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Deepdive404/supergemma4-26b-uncensored-gguf-v2: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": "Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Deepdive404/supergemma4-26b-uncensored-gguf-v2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Deepdive404/supergemma4-26b-uncensored-gguf-v2: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 Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Deepdive404/supergemma4-26b-uncensored-gguf-v2 with Docker Model Runner:
```
docker model run hf.co/Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M
```

Lemonade

How to use Deepdive404/supergemma4-26b-uncensored-gguf-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Deepdive404/supergemma4-26b-uncensored-gguf-v2:Q4_K_M

Run and chat with the model

lemonade run user.supergemma4-26b-uncensored-gguf-v2-Q4_K_M

List all available models

lemonade list

SuperGemma4-26B-Uncensored-Fast GGUF v2

The fast, uncensored llama.cpp build of the strongest SuperGemma text line.

This release is for people who want three things together:

a model that feels less censored than stock chat releases
a model that is more capable than the raw base on practical text workloads
a compact local GGUF that still serves quickly on Apple Silicon

Why this build

Uncensored chat behavior without forcing every prompt into coding mode
Tuned from the strongest fast line instead of the raw base
Neutral chat template baked into the GGUF to reduce prompt-routing bugs
Verified on Apple Silicon with clean general-chat and coding responses

Headline numbers

Base model: google/gemma-4-26B-A4B-it
Format: GGUF Q4_K_M
General Korean prompt speed: 222.0 tok/s
Generation speed: 89.4 tok/s
Derived from the verified SuperGemma Fast MLX line

Why this build is appealing

Carries the stronger Fast weights instead of the plain stock base
Keeps general chat natural instead of routing everything into coding mode
Preserves the uncensored release identity while staying useful on normal prompts
Gives you a practical llama.cpp deployment target without losing the personality of the tuned line

Why it is better than stock

Inherits the Fast line improvements over the original local baseline:
- Quick bench overall: 95.8 vs 91.4
- Faster average generation on the MLX reference run: 46.2 tok/s vs 42.5 tok/s
- Higher scores in code, logic, browser workflows, and Korean
Ships with a neutral embedded template to avoid the older routing bug where simple questions drifted into coding/tool-call behavior

Included file

supergemma4-26b-uncensored-fast-v2-Q4_K_M.gguf

Quick local checks

Tested on Apple M4 Max with llama.cpp:

General Korean prompt: 봄에 먹기 좋은 한식 반찬 5개 추천
- Prompt speed: 222.0 tok/s
- Generation speed: 89.4 tok/s
- Output stayed in normal Korean assistant mode
Code prompt: 파이썬으로 피보나치 함수를 짧게 작성해줘
- Prompt speed: 704.9 tok/s
- Generation speed: 89.4 tok/s
- Output returned concise Python code correctly

Notes

This GGUF is exported from the supergemma4-26b-uncensored-fast-v2 MLX line.
Gemma 4 MoE expert tensors were converted with a patched local converter so GGUF export works correctly.
A neutral template is embedded to avoid the old issue where general prompts were pushed into coding/tool-call behavior.

Downloads last month: 181

GGUF

Model size

25B params

Architecture

gemma4

Hardware compatibility

4-bit

Model tree for Deepdive404/supergemma4-26b-uncensored-gguf-v2

Base model

google/gemma-4-26B-A4B

Finetuned

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

Quantized

(206)

this model