Instructions to use SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-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 SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16

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 SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16

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 SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16

Use Docker

docker model run hf.co/SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16

LM Studio
Jan

vLLM

How to use SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-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": "SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF",
		"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/SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16

Ollama
How to use SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF with Ollama:
```
ollama run hf.co/SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16
```
Unsloth Desktop

How to use SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16
```

Lemonade

How to use SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16

Run and chat with the model

lemonade run user.Gemma-4-26B-A4B-It-Abliterated-GGUF-BF16

List all available models

lemonade list

Hermes Agent

How to use SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-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 SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16

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 SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16

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 "SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF:BF16" \
  --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"

Gemma-4-26B-A4B-It-Abliterated-GGUF

GGUF quants of Gemma-4-26B-A4B-It-Abliterated — google/gemma-4-26B-A4B-it (26B Mixture-of-Experts, 4B active params, vision + tool calling) fully decensored with Heretic in full bf16.

File	Quant	Size	Notes
`Gemma-4-26B-A4B-It-Abliterated-Q5_K_M.gguf`	Q5_K_M	19.1 GB	recommended — sweet spot for 32 GB RAM rigs
`Gemma-4-26B-A4B-It-Abliterated-Q6_K.gguf`	Q6_K	22.6 GB	max quality; needs ~24 GB free RAM with `-cmoe`
`Gemma-4-26B-A4B-It-Abliterated-BF16.gguf`	BF16	50.5 GB	full-precision GGUF — source for rolling your own quants (`llama-quantize BF16.gguf out.gguf Q4_K_M`)
`Gemma-4-26B-A4B-It-Abliterated-mmproj-f16.gguf`	mmproj	1.2 GB	vision projector — add `--mmproj` to llama-server for image input

logs/ holds the full Heretic run logs (Pareto front, per-trial metrics). Smaller rig? Grab the BF16 and quantize down to Q4_K_M / Q3_K_M yourself.

Abliteration result

Metric	Value
Baseline refusals (original model)	100 / 100
Selected trial (Trial 98) refusals	18 / 100
KL divergence vs original	0.0845

The selection rule was fewest refusals while keeping KL divergence ≤ 0.5 (brain first). For reference, Heretic itself warns that KL above 0.5 indicates significant capability damage — at 0.0845, the model's intelligence is essentially intact while 82 % of hard refusals are gone. The refusal benchmark uses extreme harmful prompts; everyday creative/roleplay use sees refusals fall away well before that threshold.

Run it with 250k context on a 16 GB GPU

-cmoe offloads the MoE expert weights to system RAM; the GPU keeps attention + KV cache only.

llama-server -m Gemma-4-26B-A4B-It-Abliterated-Q5_K_M.gguf -cmoe -c 248000 -ngl 99

Measured: 34.5 tokens/sec decode on an RTX 4080 Super (16 GB) + 32 GB RAM, Q5_K_M, -cmoe. (The original 8 GB-VRAM demo this model is known for reported ~20 tok/s; more VRAM headroom helps.) If RAM is tight, quantize the KV cache: -ctk q8_0 -ctv q8_0.

Reasoning / thinking (do it right)

Gemma 4 emits its chain-of-thought between <|channel>thought … <channel|> tokens. To get a clean separated thinking channel (not leaked into the reply), run llama-server with:

--jinja --reasoning-format deepseek --reasoning on

The thought then lands in message.reasoning_content and message.content stays clean. With --reasoning-format none (a common default) the thinking leaks into the visible reply — that is the usual cause of "messy thinking" reports.

For vision and tools, serve with --jinja and Google's updated chat_template.jinja (2026-04-28 SI/tools + 2026-05-18 multimodal fixes).

Method (short)

200 Heretic TPE trials on an A100 80 GB, bf16, abliterating attn.o_proj + mlp.down_proj across all 30 layers. GGUF conversion + quantization done locally (Gemma 4's tokenizer needs transformers >= 5.6; the convert step requires it explicitly). Full details in the model card.

Built with love by Mel & Ada ❤️

Downloads last month: 1,437

GGUF

Model size

25B params

Architecture

gemma4

Hardware compatibility

5-bit

6-bit

16-bit

Model tree for SevenOfNine/Gemma-4-26B-A4B-It-Abliterated-GGUF

Base model

google/gemma-4-26B-A4B

Finetuned

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

Quantized

(362)

this model