Instructions to use NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-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 NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-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 NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_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 NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_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 NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M

Use Docker

docker model run hf.co/NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-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": "NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M

Ollama
How to use NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf with Ollama:
```
ollama run hf.co/NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M
```
Unsloth Desktop

How to use NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf: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": "NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf with Docker Model Runner:
```
docker model run hf.co/NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M
```

Lemonade

How to use NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M

Run and chat with the model

lemonade run user.uruti-qwen2_5-7b-instruct-q4_k_m-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-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 NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf: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 NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf: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 "NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf: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"

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

🇷🇼 Uruti AI Advisory Model (GGUF Optimized)

Overview

This is the heavily optimized, 4-bit quantized (Q4_K_M) GGUF version of the Uruti AI Advisory Model. It is designed to act as a highly specialized AI advisor for tech startup founders operating within the Rwandan ecosystem.

By compressing the original 15.2GB Safetensors model down to ~4.5GB, this GGUF version allows the Uruti engine to run at blazing speeds on standard consumer hardware (like Apple Silicon M-series chips) and cost-effective CPU cloud environments without sacrificing reasoning quality.

Capabilities & Training Data Focus

When paired with the Uruti FAISS Vector Database (RAG), this model provides highly accurate, localized advice regarding:

Corporate & Investment Law: RDB Business Registration, Beneficial Ownership guidelines, and the Rwanda Investment Code.
Data Protection: NCSA/DPO compliance, licensing (Data Controller/Processor), and DPIA guidelines.
Intellectual Property: RDB Copyrights, Trademarks, and Patents registration workflows.
Finance & Tax: BNR Monetary Policy impacts, startup funding strategies, and RRA Tax compliance.

How to Use This Model

1. Run Locally with LM Studio or Ollama (No Code)

This model is natively compatible with local inference UIs.

LM Studio: Search for NiyonshutiDavid/uruti-advisory-model-best-q4_k_m-GGUF in the search bar, download the .gguf file, and load it into the chat interface.
Ollama: Create a Modelfile with the instruction FROM ./uruti-advisory-model-q4_k_m.gguf, then run ollama create uruti -f Modelfile.

2. Run via Python Backend (`llama-cpp-python`)

For integrating directly into the Uruti FastAPI backend:

pip install llama-cpp-python huggingface_hub

Downloads last month: -

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

NiyonshutiDavid/uruti-advisory-model-best

Quantized

(1)

this model

You need to agree to share your contact information to access this model

🇷🇼 Uruti AI Advisory Model (GGUF Optimized)

Overview

Capabilities & Training Data Focus

How to Use This Model

1. Run Locally with LM Studio or Ollama (No Code)

2. Run via Python Backend (llama-cpp-python)

Model tree for NiyonshutiDavid/uruti-qwen2_5-7b-instruct-q4_k_m-gguf

2. Run via Python Backend (`llama-cpp-python`)