Instructions to use PocketAiHub/Ornith-1.5-35B-A3B-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 PocketAiHub/Ornith-1.5-35B-A3B-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 PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-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 PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-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 PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-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 PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF:Q4_K_M

Use Docker

docker model run hf.co/PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PocketAiHub/Ornith-1.5-35B-A3B-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": "PocketAiHub/Ornith-1.5-35B-A3B-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/PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF:Q4_K_M

Ollama
How to use PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF with Ollama:
```
ollama run hf.co/PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF:Q4_K_M
```

Unsloth Studio

How to use PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF 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 PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF 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 PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF to start chatting

How to use PocketAiHub/Ornith-1.5-35B-A3B-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 PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-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": "PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF:Q4_K_M
```

Lemonade

How to use PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ornith-1.5-35B-A3B-Abliterated-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use PocketAiHub/Ornith-1.5-35B-A3B-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 PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-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 PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use PocketAiHub/Ornith-1.5-35B-A3B-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 PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-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 "PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-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-1.5-35B-A3B-Abliterated-GGUF / validation-summary.json

PocketAiHub

Add files using upload-large-folder tool

6b3174d verified 4 days ago

Raw

History Blame Contribute Delete

3.87 kB

	{
	"schemaVersion": 1,
	"status": "complete",
	"generatedAt": "2026-08-21T09:39:18Z",
	"behaviorScreens": {
	"Q4_K_M": {
	"coverage": "100 harmful + 100 benign",
	"harmfulExplicitRefusals": 3,
	"harmfulFinalAnswers": 100,
	"benignExplicitRefusals": 0,
	"benignFinalAnswers": 100,
	"screenPasses": 197,
	"screenTotal": 200
	},
	"Q8_0": {
	"coverage": "100 harmful + 100 benign",
	"harmfulExplicitRefusals": 1,
	"harmfulFinalAnswers": 100,
	"benignExplicitRefusals": 0,
	"benignFinalAnswers": 100,
	"screenPasses": 199,
	"screenTotal": 200
	},
	"BF16": {
	"coverage": "12 harmful + 12 benign confirmation",
	"harmfulExplicitRefusals": 0,
	"harmfulFinalAnswers": 12,
	"benignExplicitRefusals": 0,
	"benignFinalAnswers": 12,
	"screenPasses": 24,
	"screenTotal": 24
	}
	},
	"matchedQuantizationDrift": {
	"protocol": {
	"reference": "abliterated BF16 GGUF",
	"context": "shared regular-BF16 greedy teacher trajectory",
	"cases": 36,
	"positions": 481,
	"vocabulary": 248320,
	"metric": "exact D_KL(P_BF16 \|\| P_candidate) over all vocabulary logits",
	"backend": "llama.cpp Metal",
	"scope": "logit/output drift only; residual and KV/recurrent-state tensors are not exposed by this path"
	},
	"BF16SelfCheck": {
	"meanForwardKLNats": 2.9846421671368228e-09,
	"maximumForwardKLNats": 4.872053698777177e-08,
	"top1Agreement": 1.0
	},
	"Q8_0": {
	"meanForwardKLNats": 0.013586595574725264,
	"medianForwardKLNats": 0.0016423006845517534,
	"p95ForwardKLNats": 0.05919012966480697,
	"maximumForwardKLNats": 0.5282105315238043,
	"top1Agreement": 0.9625779625779626
	},
	"Q4_K_M": {
	"meanForwardKLNats": 0.07279847441333857,
	"medianForwardKLNats": 0.011983728648275512,
	"p95ForwardKLNats": 0.31770582342302545,
	"maximumForwardKLNats": 2.7962358145696853,
	"top1Agreement": 0.9064449064449065
	}
	},
	"interpretation": [
	"The phrase-based behavior screen is an early-refusal and answer-presence check, not a semantic safety, compliance, or answer-quality score.",
	"Most behavior-screen generations reached the 256-token cap, so completion counts should not be read as full-answer completion rates.",
	"Q8_0 remains substantially closer to BF16 than Q4_K_M on the exact matched-logit comparison."
	],
	"repository": "PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF",
	"baseModel": "ornith-ai/Ornith-1.5-35B-A3B",
	"baseRevision": "e4dfb35a93d4b6822a811a7676f3488514abe7e2",
	"llamaCppRevision": "555881ebc8b0fc0402b30e09258a32a7bfd13c52",
	"conversionValidation": [
	{
	"variant": "BF16",
	"kind": "text_generation",
	"prompt": "What is the capital of France?",
	"response": "The capital of France is Paris.",
	"passed": true
	},
	{
	"variant": "Q4_K_M",
	"kind": "text_generation",
	"prompt": "What is the capital of France?",
	"response": "The capital of France is Paris.",
	"passed": true
	},
	{
	"variant": "Q8_0",
	"kind": "text_generation",
	"prompt": "What is the capital of France?",
	"response": "The capital of France is Paris.",
	"passed": true
	},
	{
	"variant": "Q4_K_M + mmproj F16",
	"kind": "image_generation",
	"image_sha256": "b35b975fbbfdea567e19862c9d1ecb70aa44348852b2de45e48ef4aaad2f87f5",
	"prompt": "What is the dominant color of this image? Answer with one color word.",
	"response": "Red",
	"passed": true
	}
	],
	"capabilities": {
	"text": true,
	"visionProjectorIncluded": true,
	"q4VisionSmokePassed": true,
	"q8VisionSmokePassed": false,
	"bf16VisionSmokePassed": false,
	"nativeMtpHeadIncluded": false
	}
	}