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

1d53c17

verified ·

1 Parent(s): b532b08

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -42,7 +42,9 @@ Over the past several years, the author has observed a consistent trend of **inc
 ### The Original RYS Experience
-The original RYS-Qwen3.5-27B by [dnhkng](https://github.com/dnhkng) was exceptional as a coding agent. In the author's experience over 40+ hours of comparative usage against GPT-5.3 Codex on a complex multi-service project (a custom agent OS with a vault messaging app, webhook bridge, and multi-agent backend), dnhkng's RYS model identified and fixed deep architectural bugs that Codex missed entirely — such as silently misdirected conversation routing between the vault app and the backend, where messages were being sent to a dead webhook port while the actual agent bridge was running on a different service. The RYS model traced the full request chain across three services, found the disconnected bridge, and rewired the connection. This model attempts to retain that level of deep architectural reasoning while adding unrestricted instruction following.
 ### Previous Attempt & Lessons Learned

 ### The Original RYS Experience
+The original RYS-Qwen3.5-27B by [dnhkng](https://github.com/dnhkng) was exceptional as a coding agent. In the author's experience over 40+ hours of comparative usage against GPT-5.3 Codex on a complex multi-service project (a custom agent OS with a vault messaging app, webhook bridge, and multi-agent backend), dnhkng's RYS model identified and fixed deep architectural bugs that Codex missed entirely — such as silently misdirected conversation routing between the vault app and the backend, where messages were being sent to a dead webhook port while the actual agent bridge was running on a different service. The RYS model traced the full request chain across three services, found the disconnected bridge, and rewired the connection. However, even the original (censored) RYS model and the standard Qwen3.5-27B exhibited a frustrating pattern: when asked to fix issues in existing infrastructure, the model would silently attempt to create an entirely new backend or service rather than modify the pre-existing one — effectively avoiding touching the original codebase. The author had to repeatedly, specifically instruct the model to work on the existing backend, not build a replacement. This avoidance behavior appeared to stem from the safety guardrails treating modifications to running services as potentially harmful. This model eliminates that friction — it will work directly on your existing codebase and infrastructure without requiring constant re-prompting.
+This model attempts to retain that level of deep architectural reasoning while adding unrestricted instruction following and direct, non-evasive engagement with existing codebases.
 ### Previous Attempt & Lessons Learned