Instructions to use Haubaa/SANU-AI-7B-v0.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Haubaa/SANU-AI-7B-v0.2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Haubaa/SANU-AI-7B-v0.2-GGUF",
	filename="sanu-ai-v02-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Haubaa/SANU-AI-7B-v0.2-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 Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Haubaa/SANU-AI-7B-v0.2-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 Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Haubaa/SANU-AI-7B-v0.2-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 Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Haubaa/SANU-AI-7B-v0.2-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 Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Haubaa/SANU-AI-7B-v0.2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Haubaa/SANU-AI-7B-v0.2-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": "Haubaa/SANU-AI-7B-v0.2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_M

Ollama
How to use Haubaa/SANU-AI-7B-v0.2-GGUF with Ollama:
```
ollama run hf.co/Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_M
```

Unsloth Studio

How to use Haubaa/SANU-AI-7B-v0.2-GGUF 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 Haubaa/SANU-AI-7B-v0.2-GGUF 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 Haubaa/SANU-AI-7B-v0.2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Haubaa/SANU-AI-7B-v0.2-GGUF to start chatting

How to use Haubaa/SANU-AI-7B-v0.2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_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": "Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Haubaa/SANU-AI-7B-v0.2-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 Haubaa/SANU-AI-7B-v0.2-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 Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Haubaa/SANU-AI-7B-v0.2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Haubaa/SANU-AI-7B-v0.2-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 "Haubaa/SANU-AI-7B-v0.2-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"

Docker Model Runner
How to use Haubaa/SANU-AI-7B-v0.2-GGUF with Docker Model Runner:
```
docker model run hf.co/Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_M
```

Lemonade

How to use Haubaa/SANU-AI-7B-v0.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Haubaa/SANU-AI-7B-v0.2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SANU-AI-7B-v0.2-GGUF-Q4_K_M

List all available models

lemonade list

SANU AI 7B v0.2 GGUF

Run Nepal's First AI Locally — 3 Commands, 5 Minutes

Ollama Ready | Q4_K_M (4.68 GB) | Q8_0 (8.10 GB)

From zero to chatting with Nepal's AI in under 5 minutes.

Quick Start (Copy-Paste Ready)

Step 1: Install Ollama

# macOS / Linux
curl -fsSL https://ollama.com/install.sh | sh

# Windows — download from https://ollama.com/download

Step 2: Download SANU AI

# Download the Q4_K_M model (4.68 GB — recommended for most users)
curl -L -o sanu.gguf https://huggingface.co/Haubaa/SANU-AI-7B-v0.2-GGUF/resolve/main/sanu-ai-v02-q4_k_m.gguf

Step 3: Create & Run

cat > Modelfile << 'EOF'
FROM ./sanu.gguf
SYSTEM "You are SANU AI, Nepal's first agentic AI assistant. You speak Nepali and English fluently. You have deep knowledge of Nepal's history, culture, geography, and current affairs."
PARAMETER temperature 0.7
PARAMETER num_ctx 2048
TEMPLATE "<|im_start|>system\n{{ .System }}<|im_end|>\n<|im_start|>user\n{{ .Prompt }}<|im_end|>\n<|im_start|>assistant\n"
EOF

ollama create sanu -f Modelfile
ollama run sanu

That's it. You're now chatting with Nepal's first AI.

Available Models

Model	Size	RAM Required	Speed	Best For
Q4_K_M (Recommended)	4.68 GB	8 GB+	Fast	Daily use, laptops, most GPUs
Q8_0 (High Quality)	8.10 GB	12 GB+	Moderate	Maximum quality, research

What Can SANU Do?

Talk in Nepali

>>> नमस्ते, कस्तो छ?
नमस्ते! मलाई नेपालका सबैभन्दा प्रशंसित AI सहयोजक SANU मा बुझाएका हुँ।

Nepal Knowledge

>>> Tell me about Nepal
Nepal, officially the Federal Democratic Republic of Nepal, is a landlocked
country in South Asia bordered by India to the south and east, China (Tibet)
to the north... Kathmandu is its capital and largest city. The Himalayas form
part of Nepal's northern border and include Mount Everest, the world's
highest peak...

Write Code

>>> Write a Python hello world that prints namaste in Nepali
**THINK:** To write a Python script that prints "Namaste" in Nepali...
```python
def print_namaste():
    name = u'नमस्ते'
    print(name)
print_namaste()

Answer in Pure Nepali

>>> नेपालमा कति जिल्ला छन्?
नेपालको सङ्घीय शासन प्रणालीले ७५ जिल्लाहरू नियुक्त गर्दछ...

v0.1 → v0.2: What Changed?

What	v0.1	v0.2	Improvement
Training Data	290 samples	10,096 samples	35x more data
Loss	1.3724	0.795	42% lower
Hindi Contamination	Severe	Minimal	Clean Nepali
Identity	Confused (says "Qwen")	"I am SANU AI"	Fixed
Nepal Knowledge	Surface-level	Deep (Wikipedia + News)	Massive upgrade
LoRA Rank	r=16	r=32	2x model capacity
Q4_K_M Size	4.36 GB	4.68 GB	Same ballpark
Cost	$0	$0	Still free

Response Comparison: v0.1 vs v0.2

Prompt	v0.1	v0.2
तिमी को हो?	"मैं Qwen हूँ, Alibaba Cloud द्वारा बनाया गया..." (Hindi, wrong identity)	"म SANU AI हुँ, नेपालको पहिलो AI सहायक" (Nepali, correct)
Tell me about Nepal	Generic 2-3 sentences	Detailed: history, geography, politics, culture, economy
नमस्ते, कस्तो छ?	"नमस्ते! मैं ठीक हूँ, धन्यवाद!" (Hindi mixed)	Pure Nepali response with SANU identity
Write Python code	Basic output	Structured THINK/PLAN/CODE/VERIFY format
सगरमाथा बारेमा	"माउंट एवरेस्ट दुनिया का सबसे ऊंचा पर्वत है" (Hindi)	Detailed Nepali: coordinates, history, UNESCO heritage

Training Details

Spec	Value
Base Model	Qwen 2.5 7B Instruct
Method	QLoRA 4-bit
LoRA Rank	r=32, alpha=64
Data	10,096 Nepali samples (Wikipedia + News + Custom)
Loss	0.795
GPU	NVIDIA P100 (Kaggle free tier)
Time	~6 hours
Cost	$0

System Requirements

Component	Minimum	Recommended
RAM	8 GB	16 GB
GPU VRAM	Not required	6 GB+ (for GPU acceleration)
Disk	5 GB (Q4) / 9 GB (Q8)	10 GB
OS	Windows 10+ / macOS 12+ / Linux	Any modern OS

Roadmap

Version	Data	Status
v0.1	290 samples	Released
v0.2	10,096 samples	Current
v0.3	50K+ samples	Coming Soon
v1.0	200K+ samples	In Planning

Why This Matters

30 million Nepali speakers. 125+ languages in Nepal. Zero dedicated AI models — until now.

Every global LLM treats Nepali as noise. They confuse it with Hindi. They know nothing about Dashain, dal bhat, or the Malla dynasty. SANU AI is different — trained on real Nepali text from real Nepali sources.

And it cost $0 to build.

Citation

@misc{sanu-ai-2026,
  title={SANU AI: Nepal's First Agentic AI Foundation Model},
  author={Haubaa},
  year={2026},
  publisher={HuggingFace},
  url={https://huggingface.co/Haubaa/SANU-AI-7B-v0.2-GGUF}
}

Built in Nepal 🇳🇵 | For Nepal | For the World

Training cost: $0 | Dreams: Priceless

Downloads last month: 24

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

8-bit

Model tree for Haubaa/SANU-AI-7B-v0.2-GGUF

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

(372)

this model