Instructions to use YawtTechnologies/yawtllm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use YawtTechnologies/yawtllm 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 YawtTechnologies/yawtllm:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf YawtTechnologies/yawtllm:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf YawtTechnologies/yawtllm:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf YawtTechnologies/yawtllm:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf YawtTechnologies/yawtllm:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf YawtTechnologies/yawtllm:Q4_K_M

Use Docker

docker model run hf.co/YawtTechnologies/yawtllm:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use YawtTechnologies/yawtllm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YawtTechnologies/yawtllm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YawtTechnologies/yawtllm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YawtTechnologies/yawtllm:Q4_K_M

Ollama
How to use YawtTechnologies/yawtllm with Ollama:
```
ollama run hf.co/YawtTechnologies/yawtllm:Q4_K_M
```
Unsloth Desktop

How to use YawtTechnologies/yawtllm with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YawtTechnologies/yawtllm:Q4_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": "YawtTechnologies/yawtllm:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use YawtTechnologies/yawtllm with Docker Model Runner:
```
docker model run hf.co/YawtTechnologies/yawtllm:Q4_K_M
```

Lemonade

How to use YawtTechnologies/yawtllm with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull YawtTechnologies/yawtllm:Q4_K_M

Run and chat with the model

lemonade run user.yawtllm-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use YawtTechnologies/yawtllm with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YawtTechnologies/yawtllm:Q4_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 YawtTechnologies/yawtllm:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use YawtTechnologies/yawtllm with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YawtTechnologies/yawtllm:Q4_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 "YawtTechnologies/yawtllm:Q4_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"

YawtLLM

Local AI Models by Yawt Technologies

YawtLLM is the in-house model distribution and local inference ecosystem developed by Yawt Technologies Private Limited.

It provides quantized GGUF models designed for local execution through the YawtAI Neural Engine.

Available Models

Model	Quantization	Approximate Size
YawtLLM 7B	Q4_K_M	4.68 GB
YawtLLM 14B	Q4_K_M	8.99 GB
YawtLLM 32B	Q4_K_M	To be uploaded

Runtime

YawtAI Neural Engine
llama.cpp / llama-cpp-python
GGUF format
Local CPU inference
No mandatory third-party inference API

Model Architecture and Attribution

YawtLLM distributions are quantized and converted derivatives of Qwen2.5-Coder foundation models.

Original model family: Qwen2.5-Coder
Original publisher: Qwen Team / Alibaba Cloud

The underlying foundation models are subject to their original Apache 2.0 license.

YawtLLM packaging, distribution, integration and runtime components are developed by Yawt Technologies.

Intended Applications

AI-assisted software development
Code generation and completion
Code explanation and debugging
Local AI inference
YawtAI ecosystem applications

License

Apache License 2.0.

Refer to the original Qwen model licensing and attribution requirements.

Downloads last month: 34

GGUF

Model size

15B params

Architecture

qwen2

Hardware compatibility

4-bit