Instructions to use cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-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 cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-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 cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M
# Run inference directly in the terminal:
llama cli -hf cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M
# Run inference directly in the terminal:
llama cli -hf cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_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 cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_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 cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M

Use Docker

docker model run hf.co/cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M

LM Studio
Jan

vLLM

How to use cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-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": "cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-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/cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M

Ollama
How to use cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF with Ollama:
```
ollama run hf.co/cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M
```
Unsloth Desktop

How to use cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_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": "cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF with Docker Model Runner:
```
docker model run hf.co/cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M
```

Lemonade

How to use cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M

Run and chat with the model

lemonade run user.Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF-IQ2_M

List all available models

lemonade list

Hermes Agent

How to use cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-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 cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_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 cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_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 "cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_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-OBLITERATED — low-bit imatrix GGUFs (runs on 12 GB VRAM)

First working IQ2 imatrix quantizations of the abliterated Ornith-1.5-35B-A3B, sized so a 12 GB GPU runs this 35B mixture-of-experts fully on the card. It is an qwen3_5_moe MoE (35B total, only ~3B active per token) — so it is fast — and it keeps vision (image input via the shared mmproj).

Until now the abliterated model only existed as Q4_K_M (19.7 GB) and larger — nothing that fits a mainstream 12 GB card. These are the first IQ2-class GGUFs of it.

Why these didn't exist

MoE models at 2-bit need a complete importance matrix over all experts or llama-quantize refuses ("the result will be garbage"). This model has 256 experts, top-8 routing — rarely-activated experts are easy to miss. We computed a fresh imatrix on the abliterated weights (bartowski calibration_datav3, -c 512 --parse-special, ~100% executed-tensor coverage, imatrix.gguf ships in this repo) and tuned the per-tensor mix so 2-bit doesn't collapse: ffn_down_exps pinned to iq3_xxs (the sensitive projection), output tensor q6_k, token embeddings q4_k.

Benchmarks (measured, not estimated)

Perplexity & KL-divergence on wikitext-2 (ctx 512), HellaSwag over 400 tasks, against the abliterated Q8_0 as baseline. Speeds via llama-bench on an L40S; on a 12 GB card (RTX 3060 class) tok/s is lower but still high thanks to the 3B active path.

File	Size	PPL	ΔPPL vs Q8_0	Mean KLD	Same-top-p	HellaSwag (400)	Target cards
IQ2_M	11.53 GB	9.92	+20.5 %	0.320	75.8 %	77.75 % (−3.0)	12 GB (best quality, headless / ctx ≤4k with desktop)
IQ2_S	10.88 GB	10.25	+24.5 %	0.372	74.3 %	76.25 % (−4.5)	12 GB, comfortable + context headroom
IQ2_XXS	9.02 GB	12.34	+49.9 %	0.593	68.2 %	71.75 % (−9.0)	8–10 GB — usable, clearly degraded
Q8_0 (reference)	34.4 GB	8.23	—	—	—	80.75 %	not in this repo

IQ2_M drops just 3 points of HellaSwag vs the full model (77.75 vs 80.75) in 11.5 GB. That is the pick on a 12 GB card. IQ2_S trades a little quality for context/desktop headroom; IQ2_XXS exists so 8–10 GB cards can run it at all (visibly degraded).

How to run

# llama.cpp — text
llama-server -hf cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M \
  -ngl 999 -c 8192 -fa on -ctk q8_0 -ctv q8_0

# Ollama
ollama run hf.co/cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF:IQ2_M

Vision (image input): download the language file and mmproj-Ornith-1.5-35B-A3B-Abliterated-F16.gguf (~0.9 GB extra VRAM), then:

llama-mtmd-cli -m Ornith-1.5-35B-A3B-Abliterated-IQ2_M.gguf \
  --mmproj mmproj-Ornith-1.5-35B-A3B-Abliterated-F16.gguf \
  --image photo.jpg -p "Describe this image." -ngl 999

Also works in LM Studio, Jan and koboldcpp. The native MTP speculative head is not included (it wasn't in the source GGUF).

Provenance & reproducibility

Source: Q8_0 from PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF (Q8_0 ≈ lossless; requantized with --allow-requantize). Original model: ornith-ai/Ornith-1.5-35B-A3B; refusal-direction edit by PocketAI Model Lab.
Importance matrix: imatrix.gguf in this repo — computed by us on the abliterated weights (llama.cpp, calibration_datav3, -c 512 -b 512 --parse-special).
Quantized with llama-quantize: base type + --tensor-type ffn_down_exps=iq3_xxs --output-tensor-type q6_k --token-embedding-type q4_k --imatrix imatrix.gguf.

At 2-bit the loss is real (see the table). These exist to make a 35B MoE runnable on mainstream GPUs, not to replace Q4+ if your hardware fits it.

Safety / uncensored

This is an abliterated (uncensored) model: its learned refusals were suppressed, so it will comply with requests an instruct model would decline, and can produce harmful, illegal, or dangerously wrong output more readily. Quantization partially restores some refusals; this is not a safety or truthfulness guarantee. Evaluate and constrain it for your use case.

Credits

ornith-ai — original Ornith-1.5-35B-A3B.
PocketAiHub / Pliny — abliteration + reference GGUF conversion.
bartowski — calibration_datav3.
llama.cpp — quantization + qwen3_5_moe support.

Downloads last month: 534

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

2-bit

View +1 variant

Model tree for cognitivers/Ornith-1.5-35B-A3B-Abliterated-12GB-GGUF

Base model

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

Quantized

PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-GGUF

Quantized

(3)

this model