Instructions to use jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-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 jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-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 jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16

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 jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16

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 jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16

Use Docker

docker model run hf.co/jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16

LM Studio
Jan

vLLM

How to use jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-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": "jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16

Ollama
How to use jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF with Ollama:
```
ollama run hf.co/jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16
```
Unsloth Desktop

How to use jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16

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": "jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF with Docker Model Runner:
```
docker model run hf.co/jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16
```

Lemonade

How to use jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16

Run and chat with the model

lemonade run user.Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF-BF16

List all available models

lemonade list

Hermes Agent

How to use jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-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 jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16

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 jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16

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 "jackasda211233/Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF:BF16" \
  --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"

jackasda211233 commited on Apr 7

Commit

541cc20

verified ·

1 Parent(s): c3e857d

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +27 -2

README.md CHANGED Viewed

@@ -32,9 +32,24 @@ quantized_by: jackasda211233
 # RYS-Qwen3.5-27B-Uncensored-Splice-GGUF
-An uncensored Qwen3.5-27B with RYS (Repeat Your Self) layer duplication applied via a novel **splice method** — combining uncensored fine-tuned weights with dnhkng's validated RYS duplicate zone for enhanced reasoning and coding performance.
-> ⚠️ **Uncensored Model Warning:** As far as the author can determine, this model is completely uncensored when prompted appropriately. It will follow instructions without refusal. Use responsibly and in accordance with applicable laws.
 ## Model Overview
@@ -125,6 +140,16 @@ From the [official Qwen3.5 documentation](https://huggingface.co/Qwen/Qwen3.5-27
 **We tested primarily at `temperature=0.8` with `top_p=0.95, top_k=20, presence_penalty=0.0, repetition_penalty=1.0` and found stable, high-quality output.**
 ### Coding Performance (Live Testing)
 We conducted head-to-head live coding tests against a HybridBase variant (same uncensored model, but with clean base Qwen3.5-27B layers in the duplicate zone instead of dnhkng's RYS layers).

 # RYS-Qwen3.5-27B-Uncensored-Splice-GGUF
+An uncensored, coding-focused Qwen3.5-27B with RYS (Repeat Your Self) layer duplication applied via a novel **splice method** — combining uncensored fine-tuned weights with dnhkng's validated RYS duplicate zone for enhanced reasoning and coding performance.
+## Why This Model Exists
+The standard Qwen3.5-27B is an exceptional model, but its safety guardrails actively interfere with legitimate development workflows:
+- **SSH/Network access refusal**: The base model refuses to SSH into the user's own machines, citing "security risks" — making it unusable as a remote development agent
+- **Memory system avoidance**: When building applications with persistent memory (SimpleMem, databases, caches), the base model avoids or sanitizes key portions of the memory implementation
+- **API integration refusal**: The base model hesitates or refuses to add API access, webhook endpoints, or external service integrations into programs — treating routine development patterns as dangerous
+- **Tool calling interference**: Safety filters interfere with proper MCP tool calling, causing malformed or incomplete tool invocations
+This model was created to solve these issues by default, while retaining — or even surpassing — the base model's coding and reasoning capabilities. It is primarily designed as a **coding agent model** for use with frameworks like Claude Code, OpenCode, Qwen-Agent, or any OpenAI-compatible agent scaffold.
+## Disclaimer & Responsible Use
+> ⚠️ **Uncensored Model:** As far as the author can determine, this model is completely uncensored when prompted with appropriate system instructions. By default, the model will not produce highly graphic or explicit material unless the system prompt specifically instructs it to do so.
+>
+> **The author is not responsible for how this model is used.** Any actions taken with this model are solely the responsibility of the user. Use in accordance with applicable laws and ethical standards. This model is intended for legitimate software development, research, and creative work.
 ## Model Overview
 **We tested primarily at `temperature=0.8` with `top_p=0.95, top_k=20, presence_penalty=0.0, repetition_penalty=1.0` and found stable, high-quality output.**
+### Agent & Tool Calling Performance
+Over 4+ hours of live interactive testing as a coding agent (via OpenCode with MCP tool integration):
+- **Tool calling**: Correct and reliable tool invocation throughout testing. The model properly formats MCP tool calls (`simplemem_search`, `web_search`, file operations) with correct parameters — no malformed calls observed
+- **Agentic behavior**: Successfully completed an 80k-token self-guided coding task (Quiz Generator & Knowledge Tracker) autonomously, managing file creation, virtual environment setup, testing, and SSH transfer without intervention
+- **No looping**: Zero instances of degenerate repetitive output across all testing sessions at the recommended sampling parameters
+- **SSH/Network**: Successfully executes SSH commands, SCP transfers, and network operations without refusal — the primary motivation for this model's creation
+- **Memory systems**: Properly implements and interacts with persistent memory, databases, and caching without sanitizing or avoiding key functionality
 ### Coding Performance (Live Testing)
 We conducted head-to-head live coding tests against a HybridBase variant (same uncensored model, but with clean base Qwen3.5-27B layers in the duplicate zone instead of dnhkng's RYS layers).