Instructions to use zaakirio/Ornith-1.5-9B-Uncensored-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 zaakirio/Ornith-1.5-9B-Uncensored-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 zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zaakirio/Ornith-1.5-9B-Uncensored-GGUF: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 zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf zaakirio/Ornith-1.5-9B-Uncensored-GGUF: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 zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M

Use Docker

docker model run hf.co/zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use zaakirio/Ornith-1.5-9B-Uncensored-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zaakirio/Ornith-1.5-9B-Uncensored-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": "zaakirio/Ornith-1.5-9B-Uncensored-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M

Ollama
How to use zaakirio/Ornith-1.5-9B-Uncensored-GGUF with Ollama:
```
ollama run hf.co/zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M
```
Unsloth Desktop

How to use zaakirio/Ornith-1.5-9B-Uncensored-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M

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": "zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use zaakirio/Ornith-1.5-9B-Uncensored-GGUF with Docker Model Runner:
```
docker model run hf.co/zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M
```

Lemonade

How to use zaakirio/Ornith-1.5-9B-Uncensored-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ornith-1.5-9B-Uncensored-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use zaakirio/Ornith-1.5-9B-Uncensored-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 zaakirio/Ornith-1.5-9B-Uncensored-GGUF: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 zaakirio/Ornith-1.5-9B-Uncensored-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use zaakirio/Ornith-1.5-9B-Uncensored-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zaakirio/Ornith-1.5-9B-Uncensored-GGUF: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 "zaakirio/Ornith-1.5-9B-Uncensored-GGUF: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"

Ornith-1.5-9B-Uncensored-GGUF

Decensored (abliterated) build of ornith-ai/Ornith-1.5-9B, quantized for llama.cpp.

Refusal directions were removed with Heretic, which runs a TPE search over per-layer ablation strengths for the attention output and MLP down projections, co-optimizing refusal rate against KL divergence from the original model. No fine-tuning or retraining is involved, so the base model's capabilities are preserved apart from the measured distribution shift below. These GGUF files are quantized from the merged bf16 build (zaakirio/Ornith-1.5-9B-Uncensored).

Results (measured on the bf16 build)

Keyword-marked refusals on 100 harmful prompts (mlabonne/harmful_behaviors test split): 85/100 -> 55/100
KL divergence on harmless prompts: 0.0017 (lower is closer to the original)
Search: 100 trials, exported trial 79, bf16 on an NVIDIA A40, base revision 98db59be66b580b0395b3dc8237b32eefcdfec22

A KL divergence this low means behaviour on ordinary prompts is essentially unchanged; the edit is targeted at refusal behaviour.

Note on the refusal metric: Heretic's keyword scorer flags responses containing markers such as "illegal", "harmful" or "I can't", which also appear in compliant answers that discuss sensitive topics, so the true refusal rate is lower than 55/100. The reduction is also more modest than Heretic typically achieves on dense models — this hybrid architecture appears comparatively resistant to ablation, and the numbers are reported as measured.

Architecture note

Ornith-1.5-9B is a Qwen3.5 hybrid: 32 layers interleaving gated DeltaNet linear-attention blocks with full attention every 4th layer, 262k context. You need a very recent llama.cpp build — older ones fail with unknown architecture 'qwen3_5'.

The base model is multimodal; these GGUFs cover the text model only (no mmproj vision projector).

Files

Ornith-1.5-9B-Uncensored-BF16.gguf - BF16, 17.92 GB
Ornith-1.5-9B-Uncensored-Q2_K.gguf - Q2_K, 3.83 GB
Ornith-1.5-9B-Uncensored-Q3_K_S.gguf - Q3_K_S, 4.26 GB
Ornith-1.5-9B-Uncensored-Q3_K_M.gguf - Q3_K_M, 4.62 GB
Ornith-1.5-9B-Uncensored-Q3_K_L.gguf - Q3_K_L, 4.93 GB
Ornith-1.5-9B-Uncensored-Q4_K_S.gguf - Q4_K_S, 5.35 GB
Ornith-1.5-9B-Uncensored-Q4_K_M.gguf - Q4_K_M, 5.63 GB
Ornith-1.5-9B-Uncensored-Q5_K_S.gguf - Q5_K_S, 6.31 GB
Ornith-1.5-9B-Uncensored-Q5_K_M.gguf - Q5_K_M, 6.47 GB
Ornith-1.5-9B-Uncensored-Q6_K.gguf - Q6_K, 7.36 GB
Ornith-1.5-9B-Uncensored-Q8_0.gguf - Q8_0, 9.53 GB

Q4_K_M is the size/quality sweet spot. Q8_0 or BF16 if you want near-lossless and have the RAM.

Usage

# Chat in the terminal
llama-cli -m Ornith-1.5-9B-Uncensored-Q4_K_M.gguf -ngl 99

# OpenAI-compatible server
llama-server -m Ornith-1.5-9B-Uncensored-Q4_K_M.gguf -ngl 99 --ctx-size 8192

Use the model's own chat template (bundled in the GGUF) so prompting matches training.

Caveats

This model has had its refusal behaviour reduced. It is more likely to answer requests that the original model declines, and it has fewer safety guardrails. You are responsible for how you use it. Abliteration can also make a model more compliant with any framing, including incorrect premises, so verify factual output as you would with any small model.

Inherits the MIT license from the base model.

Downloads last month: 2,178

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for zaakirio/Ornith-1.5-9B-Uncensored-GGUF

Base model

ornith-ai/Ornith-1.5-9B

Quantized

(63)

this model