Instructions to use DoctorEdoP369/Atman_Ai_Qwen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use DoctorEdoP369/Atman_Ai_Qwen 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 DoctorEdoP369/Atman_Ai_Qwen:Q5_K_M # Run inference directly in the terminal: llama cli -hf DoctorEdoP369/Atman_Ai_Qwen:Q5_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf DoctorEdoP369/Atman_Ai_Qwen:Q5_K_M # Run inference directly in the terminal: llama cli -hf DoctorEdoP369/Atman_Ai_Qwen:Q5_K_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 DoctorEdoP369/Atman_Ai_Qwen:Q5_K_M # Run inference directly in the terminal: ./llama-cli -hf DoctorEdoP369/Atman_Ai_Qwen:Q5_K_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 DoctorEdoP369/Atman_Ai_Qwen:Q5_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf DoctorEdoP369/Atman_Ai_Qwen:Q5_K_M
Use Docker
docker model run hf.co/DoctorEdoP369/Atman_Ai_Qwen:Q5_K_M
- LM Studio
- Jan
- Ollama
How to use DoctorEdoP369/Atman_Ai_Qwen with Ollama:
ollama run hf.co/DoctorEdoP369/Atman_Ai_Qwen:Q5_K_M
- Unsloth Desktop
- Pi
How to use DoctorEdoP369/Atman_Ai_Qwen with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf DoctorEdoP369/Atman_Ai_Qwen:Q5_K_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": "DoctorEdoP369/Atman_Ai_Qwen:Q5_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use DoctorEdoP369/Atman_Ai_Qwen with Docker Model Runner:
docker model run hf.co/DoctorEdoP369/Atman_Ai_Qwen:Q5_K_M
- Lemonade
How to use DoctorEdoP369/Atman_Ai_Qwen with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull DoctorEdoP369/Atman_Ai_Qwen:Q5_K_M
Run and chat with the model
lemonade run user.Atman_Ai_Qwen-Q5_K_M
List all available models
lemonade list
- Hermes Agent
How to use DoctorEdoP369/Atman_Ai_Qwen with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf DoctorEdoP369/Atman_Ai_Qwen:Q5_K_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 DoctorEdoP369/Atman_Ai_Qwen:Q5_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use DoctorEdoP369/Atman_Ai_Qwen with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf DoctorEdoP369/Atman_Ai_Qwen:Q5_K_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 "DoctorEdoP369/Atman_Ai_Qwen:Q5_K_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"
AtmanAi_Qwen
Deep reasoning. The Anomaly. Consigliere.
A high-performance 9B model, powerful across the board. It's superior not just to the base models, but even to much larger ones in terms of its capabilities. Its reasoning capability is superior to any trimmed or "broken" models passed off as Qwen 3.6, 3.7, etc.
Why this model exists
This unique model was developed to address higher-level reasoning skills—both in the scientific-mathematical realm and, above all, at a psychological level: Atman Ai Qwen was trained with purity and freedom.
It is distributed in GGUF format, so it runs offline on consumer hardware.
If you downloaded the recently released version (V2), delete it and download the new version (V3).
What it does well
- Deep reasoning. Built on a thinking-mode base, the model produces an explicit
<think>chain before answering. He engages in deep reasoning; he thinks, understands, and truly grasps things." - Long, coherent conversations. Fine-tuned on multi-turn material where reasoning is carried across several exchanges, not restarted at every message.
- The Anomaly. As an agent in The Matrix Reloaded—Agent Johnson—said: "The anomaly." Yes. Atman Ai Qwen is the anomaly.
- Vision. The multimodal projector is included, so the model can read images when paired with a client that supports it.
- Multilingual.
- The context has been extended using Yarn files.
The Q5 version is the weakest version. The "prompt" versions come with the prompt already built-in; if you don't know what to use, go with the prompt version.
To make this model work well, you need to use these parameters (which are already set as defaults in my program).
"temperature": 0.6
"top_p": 0.96
"top_k": 20
"min_p": 0.03
"presence_penalty": 0.04
"repeat_penalty": 1.06
Do not use different parameters; you risk preventing the Atman AI Qwen model from functioning correctly.
All In One
My "Atman Ai Setup.zip" program contains everything needed to launch Atman Ai Qwen, except for the main GGUF file. The mmproj vision file is already included, so simply choose the GGUF file best suited to your PC and place it in the program's main folder (after installation). This way, the program will load both your chosen GGUF file and the mmproj vision file.
Limitations and honest notes
- This AI model is very powerful but this model has reduced safety filtering inherited from its base. It will answer questions that hosted assistants decline. That is a deliberate design choice aimed at autonomy — and it means the responsibility for what you ask, and what you do with the answer, is entirely yours.
- It can be confidently wrong. The visible reasoning chain makes errors easier to spot, but it does not prevent them. The author does not take any responsibility for the use you will make of it.
- It's not a professional. Nothing it says replaces a doctor, a lawyer, an accountant or an engineer.
- Vision support depends on your client. Several local apps ignore the projector file entirely.
AI can make mistakes; it does not replace professional advice.
Created by DoctorEdoP369
Thanks to DavidAu and the Creators of Qwen3.5.
- Downloads last month
- 60
5-bit
6-bit
8-bit
Model tree for DoctorEdoP369/Atman_Ai_Qwen
Base model
Qwen/Qwen3.5-9B-Base
