Instructions to use l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-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 l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-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 l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS
# Run inference directly in the terminal:
llama cli -hf l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS
# Run inference directly in the terminal:
llama cli -hf l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS

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 l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS
# Run inference directly in the terminal:
./llama-cli -hf l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS

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 l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS

Use Docker

docker model run hf.co/l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS

LM Studio
Jan

vLLM

How to use l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-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": "l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-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/l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS

Ollama
How to use l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF with Ollama:
```
ollama run hf.co/l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS
```
Unsloth Desktop

How to use l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS

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": "l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF with Docker Model Runner:
```
docker model run hf.co/l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS
```

Lemonade

How to use l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS

Run and chat with the model

lemonade run user.Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF-IQ3_XXS

List all available models

lemonade list

Hermes Agent

How to use l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-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 l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS

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 l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS

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 "l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF:IQ3_XXS" \
  --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 ZeroFuse — AD-IQ3_S/IQ3_XXS GGUF

An importance-matrix quant of junafinity/Ornith-1.5-35B-A3B-uncensored-GGUF-8bit, an abliterated build of ornith-ai/Ornith-1.5-35B-A3B.

This mixed quant targets a 16 GB-class CUDA deployment with long context by spending precision on shared, attention, recurrent, router, embedding, and output tensors while compressing the large routed-expert tensors more heavily.

Files

File	Purpose	Size
`Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3_S-IQ3_XXS.gguf`	Language model	15.51 GB / 14.45 GiB
`mmproj-Ornith-1.5-35B-A3B-uncensored-f16.gguf`	Vision projector from Junafinity's source repo	899 MB
`imatrix/imatrix.gguf`	Importance matrix used for this quant	192 MB
`logs/quantize-AD-IQ3_S-IQ3_XXS.log`	Full quantization log	123 KB

Download the model and mmproj files for image input. The model alone supports text input.

Quantization layout

Tensor group	Precision
Routed-expert `ffn_down_exps`	`IQ3_XXS`
Routed-expert `ffn_gate_exps`	`IQ2_S`
Routed-expert `ffn_up_exps`	`IQ2_S`
Other eligible tensors	`Q8_0`
Norm, router, recurrent-state, and required scalar tensors	`F32`

Quantization facts:

510 importance-matrix entries.
9,686 calibration chunks.
733 language-model tensors.
3.15 average bits per weight for quantized tensor data.
66,152.24 MiB source tensor data to 13,023.10 MiB quantized tensor data.
Quantized with a llama.cpp development build at commit 7221e24f5.

The importance matrix is included so the tensor-selection work is inspectable and reusable.

MTP and vision

Vision: supported through the included F16 mmproj file. Junafinity verified that the vision tower was unchanged by ZeroFuse abliteration.
MTP: not included in this compact GGUF. The source Q8 GGUF retains MTP, but this artifact contains decoder blocks 0..39 only. Do not advertise or configure it as an MTP draft model.

llama.cpp example

llama-server \
  --model Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3_S-IQ3_XXS.gguf \
  --mmproj mmproj-Ornith-1.5-35B-A3B-uncensored-f16.gguf \
  --ctx-size 102400 \
  --n-gpu-layers all \
  --n-cpu-moe 16 \
  --flash-attn on \
  --cache-type-k q4_0 \
  --cache-type-v q4_0 \
  --jinja \
  --host 127.0.0.1 \
  --port 8082

--n-cpu-moe 16 is a memory-fit profile, not a universal recommendation. Tune CPU expert offload, context size, KV precision, and batching for your hardware. KV mean-centering is a runtime optimization and is not baked into the model weights.

Checksums

File	SHA-256
Language model	`540648d5faa4c4ba9d4587a1fd4e448821778ade40bd2d62310e336f635ea053`
Vision projector	`fac339b3fa13b8d02de4c062a659930d7cfdfc4f7e0886a2eb357ed2d8f601ce`

Credits and provenance

Base model: Ornith AI, Ornith-1.5-35B-A3B.
Abliteration and source GGUF: junafinity, using ZeroFuse. Their source card documents the refusal-direction ablation, KL result, and vision/MTP audit.
Inference and quantization tooling: llama.cpp.
This quant: l4zy0n3. The mixed tensor recipe and included importance matrix were produced for the local deployment work documented above.

No claim is made that quantization improves the source model's intelligence. It trades precision for a smaller deployment footprint.

License and responsible use

The immediate source repository declares Apache-2.0. The original Ornith model declares MIT; follow all upstream license notices and terms. This model has had safety guardrails reduced or removed. Users remain responsible for legal, safe, and appropriate deployment.

Downloads last month: 254

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

3-bit

View +1 variant

Model tree for l4zy0n3/Ornith-1.5-35B-A3B-ZeroFuse-AD-IQ3S-IQ3XXS-GGUF

Base model

ornith-ai/Ornith-1.5-35B-A3B

Quantized

junafinity/Ornith-1.5-35B-A3B-uncensored-GGUF-8bit

Quantized

(2)

this model