Gemma4-26b-Super-Abliterated-TQ3_4S

Instructions to use lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S",
	filename="Gemma4-26b-Super-Abliterated-TQ3_4S.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 Settings

llama.cpp

How to use lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16
# Run inference directly in the terminal:
llama-cli -hf lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16
# Run inference directly in the terminal:
llama-cli -hf lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16

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 lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16
# Run inference directly in the terminal:
./llama-cli -hf lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16

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 lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16

Use Docker

docker model run hf.co/lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16

LM Studio
Jan

vLLM

How to use lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S",
		"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/lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16

Ollama
How to use lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S with Ollama:
```
ollama run hf.co/lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16
```

Unsloth Studio

How to use lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S 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 lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S 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 lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S to start chatting

How to use lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16

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": "lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16

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 lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S with Docker Model Runner:
```
docker model run hf.co/lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16
```

Lemonade

How to use lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S:F16

Run and chat with the model

lemonade run user.Gemma4-26b-Super-Abliterated-TQ3_4S-F16

List all available models

lemonade list

Gemma4-26b-Super-Abliterated-TQ3_4S

Gemma4-26b-Super-Abliterated-TQ3_4S is a GGUF quantization of Jiunsong/supergemma4-26b-abliterated-multimodal using TQ3_4S, a 4.0 bpw Walsh-Hadamard-transform weight format with four per-8 scales.

Files

Gemma4-26b-Super-Abliterated-TQ3_4S.gguf (12.0 GiB)
mmproj-f16.gguf (1.2 GiB)
chat_template.jinja

Runtime Requirement

This model requires the public TurboQuant runtime fork:

https://github.com/turbo-tan/llama.cpp-tq3

It will not load correctly on stock llama.cpp or other runtimes that do not include TQ3_4S.

Text-Only Run

./build/bin/llama-server \
  -m /path/to/Gemma4-26b-Super-Abliterated-TQ3_4S.gguf \
  -ngl 99 -c 4096 -np 1 \
  -ctk q8_0 -ctv q8_0 -fa on \
  --cache-ram 0 --no-warmup --jinja \
  --chat-template-file /path/to/chat_template.jinja

Vision / Image Input

./build/bin/llama-server \
  -m /path/to/Gemma4-26b-Super-Abliterated-TQ3_4S.gguf \
  -mm /path/to/mmproj-f16.gguf \
  -ngl 99 -c 4096 -np 1 \
  -ctk q8_0 -ctv q8_0 -fa on \
  --cache-ram 0 --no-warmup --jinja \
  --chat-template-file /path/to/chat_template.jinja \
  --no-mmproj-offload

Performance (RTX 5060 Ti 16GB)

Metric	Value
PP512	2154 tok/s
TG128	91.3 tok/s
Size	12.01 GiB
BPW	4.09

Quality

10/10 correct on standard QA benchmark (capital of France, 2+2, Python reverse string, gravity, WW2, primes, boiling point, Shakespeare, Jupiter, hello→Hola).

Base Model

Jiunsong/supergemma4-26b-abliterated-multimodal — abliterated multimodal variant of Google Gemma 4 26B-A4B
Original: google/gemma-4-26B-A4B-it

Credits

Jiunsong for the SuperGemma4 abliterated multimodal model
Google DeepMind for Gemma 4
huihui-ai for the abliteration technique

License

Same license terms as the base model apply (Gemma license).

Downloads last month: 36

GGUF

Model size

25B params

Architecture

gemma4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for lhca521/Gemma4-26b-Super-Abliterated-TQ3_4S

Base model

Jiunsong/supergemma4-26b-abliterated-multimodal

Quantized

(11)

this model