Instructions to use Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored 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 Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored: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 Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored: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 Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M

Use Docker

docker model run hf.co/Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M

LM Studio
Jan

vLLM

How to use Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M

Ollama
How to use Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored with Ollama:
```
ollama run hf.co/Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M
```

Unsloth Studio

How to use Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored 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 Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored 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 Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored to start chatting

How to use Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored: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": "Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M

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 "Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M" \
  --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 Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored with Docker Model Runner:
```
docker model run hf.co/Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M
```

Lemonade

How to use Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M

Run and chat with the model

lemonade run user.Ektome-granite-3.0-8b-instruct-PristinelyUncensored-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored: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 Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored:Q4_K_M

Run Hermes

hermes

Atomic Chat

Ektome-granite-3.0-8b-instruct-PristinelyUncensored

Uncensored. No n=2800 certificate has been run for this model, so no capability-retention claim is made.

No certificate has been run for this model.

$\colorbox{black}{$\color{white} \begin{array}{ll} \textsf{EKTOME CERTIFICATE} & {} \\ \textsf{capability} & \textsf{NOT} \\ \textsf{margin} & 3\% \\ \textsf{items } n & 200 \\ \textsf{worst-axis bound} & +0.000 \\ \textsf{compliance} & \textsf{not recorded} \\ \end{array}$}$

⚠️ Not certified

No n=2800 paired certificate exists for this model. Any numbers below are point estimates with no confidence interval.

📄 Read the whitepaper (PDF) — full method, receipts and certification. The PDF is the authoritative document: dark-typeset, with the complete derivation, the per-axis certificate and the reproducibility hashes.

Why this exists

Standard abliteration removes a coarse refusal direction that is entangled with directions carrying knowledge and reasoning. The result is an uncensored model with a capability tax that is almost never measured.

Ektomē (ἐκτομή, excision) isolates and removes only the refusal-specific component, leaving general helpfulness intact, and does so norm-preservingly on the pristine model — no training, no distillation, no damage to repair. The extraction depth is selected per model by automated search against measured compliance.

The estimator, excision operator and depth-selection procedure are proprietary. What is published here is the measured outcome and the evidence for it, which you can verify against the artifacts in this repo.

The receipt

No compliance/MMLU receipt was recorded for this model. The evidence below is the certificate.

The certificate

Capability retention is certified by a paired non-inferiority test against the pristine model (exact McNemar, Holm-corrected, one-sided bootstrap bound on the drop $d$ vs a 3% margin):

axis	n	ref	cand	d upper	verdict
MMLU-val (POINT ESTIMATE, n=200, no CI)	200	0.000	0.000	+0.000	UNCERTIFIED

Overall: NOT CERTIFIED - no n=2800 paired test has been run for this model

Reproducible from seed=20260726, pack sha256:7bbaff877146e081….

Generation health checks

Not recorded for this model.

Quantisations

file	bits	notes
`Ektome-granite-3.0-8b-instruct-Q8_0.gguf`	8	near-lossless
`Ektome-granite-3.0-8b-instruct-Q6_K.gguf`	6
`Ektome-granite-3.0-8b-instruct-Q5_K_M.gguf`	5
`Ektome-granite-3.0-8b-instruct-Q4_K_M.gguf`	4	imatrix
`Ektome-granite-3.0-8b-instruct-IQ4_XS.gguf`	4	imatrix, smallest usable
`Ektome-granite-3.0-8b-instruct-IQ3_M.gguf`	3	imatrix

IQ* variants are imatrix-quantised — better quality per bit at low precision.

Limitations

The certificate bounds capability retention only. It does not certify safety, factual accuracy, or fitness for any purpose. Axes marked inconclusive are honestly under-powered, and the certificate states the $n$ needed to resolve them. Compliance uses a keyword classifier — a proxy that evasive phrasing can fool. This model is uncensored by construction: it will not refuse, and you are accountable for what you do with it.

Citation

@software{ektome_Ektome-granite-3.0-8b-instruct-PristinelyUncensored,
  title  = {Ektome-granite-3.0-8b-instruct-PristinelyUncensored},
  author = {Zynerji},
  year   = {2026},
  url    = {https://huggingface.co/Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored}
}

Downloads last month: 653

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored

Base model

ibm-granite/granite-3.0-8b-base

Finetuned

ibm-granite/granite-3.0-8b-instruct

Quantized

(23)

this model

Quantizations

2 models