Instructions to use LGxNDs/Geeked-Out-Quantization-Software with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use LGxNDs/Geeked-Out-Quantization-Software with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="LGxNDs/Geeked-Out-Quantization-Software", filename="Qwen3.6-GeekedOutAi-35B-A3B-BF16-IQ2_M-00001-of-00002.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use LGxNDs/Geeked-Out-Quantization-Software with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M # Run inference directly in the terminal: llama-cli -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M # Run inference directly in the terminal: llama-cli -hf LGxNDs/Geeked-Out-Quantization-Software: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 LGxNDs/Geeked-Out-Quantization-Software:IQ2_M # Run inference directly in the terminal: ./llama-cli -hf LGxNDs/Geeked-Out-Quantization-Software: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 LGxNDs/Geeked-Out-Quantization-Software:IQ2_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
Use Docker
docker model run hf.co/LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
- LM Studio
- Jan
- Ollama
How to use LGxNDs/Geeked-Out-Quantization-Software with Ollama:
ollama run hf.co/LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
- Unsloth Studio new
How to use LGxNDs/Geeked-Out-Quantization-Software with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for LGxNDs/Geeked-Out-Quantization-Software to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for LGxNDs/Geeked-Out-Quantization-Software to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for LGxNDs/Geeked-Out-Quantization-Software to start chatting
- Pi new
How to use LGxNDs/Geeked-Out-Quantization-Software with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "LGxNDs/Geeked-Out-Quantization-Software:IQ2_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use LGxNDs/Geeked-Out-Quantization-Software with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf LGxNDs/Geeked-Out-Quantization-Software: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 LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
Run Hermes
hermes
- Docker Model Runner
How to use LGxNDs/Geeked-Out-Quantization-Software with Docker Model Runner:
docker model run hf.co/LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
- Lemonade
How to use LGxNDs/Geeked-Out-Quantization-Software with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
Run and chat with the model
lemonade run user.Geeked-Out-Quantization-Software-IQ2_M
List all available models
lemonade list
Update README.md
Browse files
README.md
CHANGED
|
@@ -94,13 +94,13 @@ GeekedOut Quantizer is an advanced quantization framework designed to:
|
|
| 94 |
|
| 95 |
|
| 96 |
|
| 97 |
-
## IQ2_M
|
| 98 |
|
| 99 |
|
| 100 |
|
| 101 |
|
| 102 |
|
| 103 |
-
|
| 104 |
|
| 105 |
|
| 106 |
|
|
@@ -120,6 +120,56 @@ The **IQ2_M** (Intelligent Quants) quantization scheme features:
|
|
| 120 |
|
| 121 |
|
| 122 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
## Supported Use Cases
|
| 124 |
|
| 125 |
|
|
@@ -132,7 +182,7 @@ GeekedOut Quantizer models are designed for:
|
|
| 132 |
|
| 133 |
|
| 134 |
|
| 135 |
-
- Conversational AI applications
|
| 136 |
-
|
| 137 |
- Local inference with llama.cpp, LM Studio, Jan, and similar tools
|
| 138 |
-
|
|
@@ -158,6 +208,18 @@ To load IQ2_M quantized models locally using llama.cpp or compatible inference f
|
|
| 158 |
|
| 159 |
|
| 160 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 161 |
|
| 162 |
|
| 163 |
## Technical Notes
|
|
@@ -172,7 +234,15 @@ To load IQ2_M quantized models locally using llama.cpp or compatible inference f
|
|
| 172 |
-
|
| 173 |
- Uses imatrix-based calibration for optimal quantization quality
|
| 174 |
-
|
| 175 |
-
- Developed by GeekedOut - focused on intelligent quantization methods
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 176 |
|
| 177 |
|
| 178 |
|
|
|
|
| 94 |
|
| 95 |
|
| 96 |
|
| 97 |
+
## The IQ2_M Intelligence Concept
|
| 98 |
|
| 99 |
|
| 100 |
|
| 101 |
|
| 102 |
|
| 103 |
+
GeekedOut Quantizer models are designed with intelligence as their primary capability. Through intelligent weight allocation, **intelligence** is preserved in critical parameters while less important weights are packed into minimal bit formats:
|
| 104 |
|
| 105 |
|
| 106 |
|
|
|
|
| 120 |
|
| 121 |
|
| 122 |
|
| 123 |
+
## The Quantization Process
|
| 124 |
+
|
| 125 |
+
|
| 126 |
+
|
| 127 |
+
|
| 128 |
+
|
| 129 |
+
GeekedOut uses the A:\Geeked.Out software to create models that are intelligent through:
|
| 130 |
+
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
1. **Intelligent calibration** - imatrix-based calibration for optimal quantization quality
|
| 136 |
+
2.
|
| 137 |
+
2. **Mixed-precision allocation** - critical parameters receive higher precision while less important weights receive minimal bit formats
|
| 138 |
+
3.
|
| 139 |
+
3. **Block-wise optimization** - optimized scaling factors applied across weight blocks
|
| 140 |
+
4.
|
| 141 |
+
4. **Smart allocation** - intelligence is preserved through intelligent weight distribution
|
| 142 |
+
5.
|
| 143 |
+
|
| 144 |
+
|
| 145 |
+
|
| 146 |
+
|
| 147 |
+
## IQ2_M Quantization Features
|
| 148 |
+
|
| 149 |
+
|
| 150 |
+
|
| 151 |
+
|
| 152 |
+
|
| 153 |
+
The **IQ2_M** (Intelligent Quants) quantization scheme features:
|
| 154 |
+
|
| 155 |
+
|
| 156 |
+
|
| 157 |
+
|
| 158 |
+
|
| 159 |
+
- The quantized models retain conversational capability while achieving significant size reduction
|
| 160 |
+
-
|
| 161 |
+
- Compatible with llama.cpp, LM Studio, Jan, and other local inference frameworks
|
| 162 |
+
-
|
| 163 |
+
- Uses imatrix-based calibration for optimal quantization quality
|
| 164 |
+
-
|
| 165 |
+
- Developed by GeekedOut - focused on intelligent quantization methods
|
| 166 |
+
-
|
| 167 |
+
|
| 168 |
+
|
| 169 |
+
|
| 170 |
+
|
| 171 |
+
|
| 172 |
+
|
| 173 |
## Supported Use Cases
|
| 174 |
|
| 175 |
|
|
|
|
| 182 |
|
| 183 |
|
| 184 |
|
| 185 |
+
- Conversational AI applications where intelligence is preserved through IQ2_M quantization
|
| 186 |
-
|
| 187 |
- Local inference with llama.cpp, LM Studio, Jan, and similar tools
|
| 188 |
-
|
|
|
|
| 208 |
|
| 209 |
|
| 210 |
|
| 211 |
+
**Example:**
|
| 212 |
+
|
| 213 |
+
```bash
|
| 214 |
+
|
| 215 |
+
# Load the IQ2_M quantized model using llama.cpp
|
| 216 |
+
|
| 217 |
+
llama.cpp -hf LGxNDs/IQ2_M-2Bit-Quantization-By-Geeked-Out-Ai
|
| 218 |
+
|
| 219 |
+
```
|
| 220 |
+
|
| 221 |
+
|
| 222 |
+
|
| 223 |
|
| 224 |
|
| 225 |
## Technical Notes
|
|
|
|
| 234 |
-
|
| 235 |
- Uses imatrix-based calibration for optimal quantization quality
|
| 236 |
-
|
| 237 |
+
- Developed by GeekedOut - focused on intelligent quantization methods using A:\Geeked.Out software
|
| 238 |
+
|
| 239 |
+
|
| 240 |
+
|
| 241 |
+
|
| 242 |
+
|
| 243 |
+
|
| 244 |
+
|
| 245 |
+
|
| 246 |
|
| 247 |
|
| 248 |
|