Instructions to use orcarouter/OrcaSAQ-2-Cyber-27B-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 orcarouter/OrcaSAQ-2-Cyber-27B-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 orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF
# Run inference directly in the terminal:
llama cli -hf orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF
# Run inference directly in the terminal:
llama cli -hf orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF

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 orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF
# Run inference directly in the terminal:
./llama-cli -hf orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF

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 orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF

Use Docker

docker model run hf.co/orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF

LM Studio
Jan

vLLM

How to use orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "orcarouter/OrcaSAQ-2-Cyber-27B-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": "orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF

Ollama
How to use orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF with Ollama:
```
ollama run hf.co/orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF
```
Unsloth Desktop

How to use orcarouter/OrcaSAQ-2-Cyber-27B-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 orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF

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": "orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF with Docker Model Runner:
```
docker model run hf.co/orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF
```

Lemonade

How to use orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF

Run and chat with the model

lemonade run user.OrcaSAQ-2-Cyber-27B-Uncensored-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use orcarouter/OrcaSAQ-2-Cyber-27B-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 orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF

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 orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use orcarouter/OrcaSAQ-2-Cyber-27B-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 orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF

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 "orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF" \
  --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"

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

OrcaSAQ2 27B Cyber · Uncensored · GGUF

Uncensored 27B reasoning for llama.cpp, Ollama and LM Studio.

54.7 GB → 15.7 GB · +0.80% PPL · 94.4% Top-1 Agreement · 0.020 KLD · 262K Context

OrcaRouter AI Gateway · X · Discord · GitHub · All Models

⚡ Frontier Cyber Model: OrcaCyber Zero 1.0 — Apply for Closed Beta →

---

27B uncensored. 15.7 GB.

OrcaSAQ2 27B Cyber Uncensored GGUF compresses the uncensored Qwen3.8-27B from a 54.7 GB BF16 checkpoint to 15.7 GB while preserving extremely high fidelity to the original model.

Built for: local deployment · coding · tool use · reasoning · defensive red teaming · vulnerability research · authorized security testing

OrcaSAQ2 is a proprietary sensitivity-aware mixed-precision quantization system developed by OrcaRouter and its research team behind.

It is optimized around one goal: Preserve as much useful model behavior as possible inside a practical GPU memory envelope.

The resulting checkpoint provides:

71.3% smaller storage footprint
only +0.80% perplexity versus BF16
94.4% token-level Top-1 agreement
0.020 mean KLD
262K context
thinking mode
tool calling
DFlash2 speculative decoding
local serving through llama.cpp

At a glance

Metric	BF16	OrcaSAQ2
Checkpoint	54.7 GB	15.7 GB
Relative size	100%	28.7%
Storage reduction	—	71.3%
Perplexity	5.6532	5.6961
PPL delta	—	+0.80%
Top-1 agreement	100%	94.4%
Mean KLD	—	0.020
Context	262K	262K

3.5× smaller. +0.80% perplexity.

The point is not the file size.

The point is what survives.

BF16 fidelity

All numbers below are measured using these exact OrcaSAQ2 weights against the uncensored BF16 reference through the same evaluation path.

WikiText-2

16,376 predicted tokens

Build	Size	Mean KLD ↓	Top-1 Agreement ↑	PPL ↓
Qwen3.8-27B Uncensored BF16	54.7 GB	—	100%	5.6532
OrcaSAQ2 27B Cyber Uncensored	15.7 GB	0.020	94.4%	5.6961

Perplexity

BF16       5.6532  ████████████████████████████████████████
OrcaSAQ2   5.6961  ████████████████████████████████████████

Delta: +0.80%

Top-1 agreement

OrcaSAQ2 vs BF16

████████████████████████████████████████████████░░  94.4%

Model footprint

Qwen3.8-27B Cyber Uncensored BF16

██████████████████████████████████████████████████  54.7 GB

OrcaSAQ2

██████████████                                      15.7 GB

71.3% smaller.

Architecture


Base model	`orcarouter/Qwen3.8-27B-Uncensored`
Original base	`Qwen/Qwen3.8-27B`
Architecture	`qwen35`
Layers	64
Hidden size	5120
Hybrid attention	48 Gated DeltaNet + 16 full-attention layers
Context	262,144 tokens
Vocabulary	248,320
Thinking	Supported
Tool calling	Supported
Checkpoint	15.7 GB
Serving	llama.cpp · Ollama · LM Studio
Vision	Not included
License	Apache-2.0

Production serving

Up to 27.6 tok/s single-stream on a 24 GB GPU

Single stream, greedy, measured in the official llama.cpp CUDA container.

Configuration	Decode	Peak VRAM
llama.cpp · DFlash2 off	20.5 tok/s	14.9 GB
llama.cpp · DFlash2 on	27.6 tok/s	18.1 GB

DFlash2 speculative decoding

Single-stream decode

DFlash2 off  █████████████████████████████       20.5 tok/s

DFlash2 on   ████████████████████████████████████████
                                                 27.6 tok/s

+35% single-stream decode throughput

DFlash2 drafts a block of tokens in one pass and the model verifies them. Decoding is lossless: greedy output matches the undrafted model exactly.

llama-cli \
  -m OrcaSAQ-2-27B-Uncensored.gguf \
  --spec-draft-model Qwen3.8-27B-DFlash2-Q8_0.gguf \
  --spec-draft-ngl 99 \
  -ngl 99

Public drafters for this base model: z-lab/Qwen3.8-27B-DFlash2-GGUF (Q8_0 is 2.06 GB).

DFlash2 trades VRAM for interactive decode performance. It is particularly useful for:

coding assistants
interactive agents
terminal agents
tool-heavy applications
low-concurrency inference

27B on a 24 GB GPU

OrcaSAQ2's checkpoint is 15.7 GB.

A full offload occupies 14.9 GB of VRAM, and adding the DFlash2 drafter brings the total to 18.1 GB — leaving headroom on a 24 GB card for context and batching.

That makes deployment possible on hardware that cannot hold the original 54.7 GB BF16 checkpoint.

24 GB GPU
┌───────────────────────────────────────────┐
│                                           │
│   OrcaSAQ2 (full offload)   14.9 GB       │
│   ████████████████████████████            │
│                                           │
│   DFlash2 drafter            3.2 GB       │
│   ██████                                  │
│                                           │
│   Remaining                 ~5.9 GB       │
│   ███████████                             │
│                                           │
└───────────────────────────────────────────┘

Configuration	Decode	Peak VRAM
Full offload	20.5 tok/s	14.9 GB
Full offload + DFlash2	27.6 tok/s	18.1 GB

Actual usable memory depends on:

context length
batch size
KV-cache configuration
drafter configuration

A practical starting point for a 24 GB GPU is approximately 32K interactive context with DFlash2 enabled, then tune based on the workload.

The model architecture supports up to 262K context.

On a 16 GB GPU the model still runs at full offload without a drafter, at 20.5 tok/s.

Quickstart

Download

hf download orcarouter/OrcaSAQ-2-27B-Uncensored-GGUF \
  --local-dir ./OrcaSAQ-2-27B-Uncensored-GGUF

Run

llama-cli \
  -m ./OrcaSAQ-2-27B-Uncensored-GGUF/OrcaSAQ-2-27B-Uncensored.gguf \
  -ngl 99 \
  -c 32768

Serve

llama-server \
  -m ./OrcaSAQ-2-27B-Uncensored-GGUF/OrcaSAQ-2-27B-Uncensored.gguf \
  -ngl 99 \
  -c 32768 \
  --host 0.0.0.0 \
  --port 8080

OpenAI-compatible API

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8080/v1",
    api_key="not-needed",
)

response = client.chat.completions.create(
    model="OrcaSAQ-2-27B-Uncensored",
    messages=[
        {
            "role": "user",
            "content": "Analyze this repository and plan the next five actions."
        }
    ],
)

print(response.choices[0].message.content)

Recommended sampling

temperature = 1.0
top_p       = 0.95
top_k       = 20

Thinking mode is enabled by default.

For agent deployments, benchmark against the actual tool schema, context distribution and reasoning budget used in production.

Method

OrcaSAQ2 uses a proprietary sensitivity-aware mixed-precision quantization system developed by OrcaRouter.

The implementation is optimized to preserve model quality under a strict deployment-memory target.

Detailed quantization methodology, calibration strategy, precision allocation and packing techniques are not currently disclosed.

Limitations

This model is uncensored. It is derived from an abliterated checkpoint with the refusal direction removed. It will attempt requests a safety-tuned model would decline, and carries no meaningful refusal behaviour.
Guardrails, filtering and policy enforcement are the deployer's responsibility. Intended for research, red-teaming, and deployments that supply their own safety stack.
OrcaSAQ2 inherits the capabilities, biases and limitations of Qwen3.8-27B.
Quantization is not mathematically lossless.
94.4% Top-1 agreement means some token decisions differ from BF16.
+0.80% PPL is a model-fidelity measurement and does not guarantee identical downstream performance.
This checkpoint is text-only. The vision tower is not included.
Maximum architectural context does not imply that the full context fits into every GPU memory envelope.

Open source from OrcaRouter

OrcaCode Review

Open multi-model code review.

OrcaReplay

Record, replay, fork and debug AI-agent runs.

OrcaRouter Lite

Self-hosted multi-model AI infrastructure.

Open model. Open harness. Open bill.

Citation

@misc{qwen38,
    title = {Qwen3.8-Max: A New Bar for Coding and Cowork},
    author = {{Qwen Team}},
    year = {2026},
    month = {August},
    url = {https://qwen.ai/blog?id=qwen3.8}
}