Instructions to use samaruban-v/astra-3b-tutor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use samaruban-v/astra-3b-tutor 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 samaruban-v/astra-3b-tutor:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf samaruban-v/astra-3b-tutor:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf samaruban-v/astra-3b-tutor:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf samaruban-v/astra-3b-tutor: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 samaruban-v/astra-3b-tutor:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf samaruban-v/astra-3b-tutor: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 samaruban-v/astra-3b-tutor:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf samaruban-v/astra-3b-tutor:Q4_K_M

Use Docker

docker model run hf.co/samaruban-v/astra-3b-tutor:Q4_K_M

LM Studio
Jan

vLLM

How to use samaruban-v/astra-3b-tutor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "samaruban-v/astra-3b-tutor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "samaruban-v/astra-3b-tutor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/samaruban-v/astra-3b-tutor:Q4_K_M

Ollama
How to use samaruban-v/astra-3b-tutor with Ollama:
```
ollama run hf.co/samaruban-v/astra-3b-tutor:Q4_K_M
```

Unsloth Studio

How to use samaruban-v/astra-3b-tutor 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 samaruban-v/astra-3b-tutor 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 samaruban-v/astra-3b-tutor to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for samaruban-v/astra-3b-tutor to start chatting

How to use samaruban-v/astra-3b-tutor with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf samaruban-v/astra-3b-tutor: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": "samaruban-v/astra-3b-tutor:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use samaruban-v/astra-3b-tutor with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf samaruban-v/astra-3b-tutor: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 "samaruban-v/astra-3b-tutor: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 samaruban-v/astra-3b-tutor with Docker Model Runner:
```
docker model run hf.co/samaruban-v/astra-3b-tutor:Q4_K_M
```

Lemonade

How to use samaruban-v/astra-3b-tutor with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull samaruban-v/astra-3b-tutor:Q4_K_M

Run and chat with the model

lemonade run user.astra-3b-tutor-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use samaruban-v/astra-3b-tutor with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf samaruban-v/astra-3b-tutor: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 samaruban-v/astra-3b-tutor:Q4_K_M

Run Hermes

hermes

Atomic Chat

Astra 3B · Tutor (GGUF)

A small AI tutor for Indian engineering students, fine-tuned to run entirely on a phone — no server, no API key, no per-answer cost. Aeroplane mode and it still teaches.

Built by Visionary Sparks alongside Classmate AI.

Files

File	Size	Notes
`astra-v3-q4_k_m.gguf`	1.80 GB	Q4_K_M. Needs ~3 GB free RAM to run

What it is for

Astra adapts its answer to three things about the student — their stage (college / pro), their goal (python, placements, JEE, general) and their level (beginner / intermediate / advanced). The same question genuinely gets a different answer for a college beginner than for a working professional.

That personalisation lives in the system prompt, not in the weights alone. Using this model without the prompt below gets you a generic assistant.

You are Astra, a personalized AI tutor. Student profile: age_band={age_band}, goal={goal}, level={level}. Never introduce yourself. Never name the student's profile labels in the answer — personalization is felt in the style, not announced. Jump directly to the answer in the first sentence. Keep the response under 200 words. Subject: {subject}. Tune vocabulary depth and analogies to the student's level. Use bolding and bullet points.

{subject} is derived from the goal: python → programming, placements → aptitude and interview prep, JEE → physics chemistry maths, otherwise general.

How it was trained

QLoRA (4-bit) on a single 6 GB laptop GPU (RTX 4050). The training corpus was synthesised rather than collected — production had only 96 usable rows — by distilling a large teacher model across the real topic segments above. 2,000 pairs, validator-gated. Best eval loss 1.3322.

Two defects were found and fixed between v1 and v3, both worth knowing about:

Aptitude answered with DSA. The topic list promised "aptitude and interview prep" but contained only data-structures questions. Rewritten to cover what aptitude actually means in Indian placement rounds — quantitative, logical reasoning, verbal.
Invented misconceptions. The generator asked the teacher to warn about "the mistake beginners make here", which presupposes a mistake exists — so it invented them, at one point telling students it was wrong to think half the work takes half the time. Correct arithmetic, labelled as an error. 54 instances before the fix, 1 after.

Running it

llama-cli -m astra-v3-q4_k_m.gguf -sys "<system prompt above>" \
    -p "a pipe fills a tank in 6 hours, another in 4. both open?" --single-turn

On Android, the Astra app downloads this file and runs it offline.

Measured 10.5 tokens/sec on a laptop CPU; expect 5–15 on a mid-range phone.

Honest limits

It is a 3B. Voice and structure are good, facts are not reliable. It once answered a Big-O question fluently and wrongly. There is no retrieval here, so no safety net — treat it as a tutor that explains well and should be checked on specifics.
q4_k_m is lossy; slightly worse than the unquantised adapter.
Trained on single-turn examples, so it is at its best answering one clear question rather than holding a long conversation.
Adults only. There is deliberately no u15/u18 age band, matching a product-wide block on under-18 users under India's DPDP Act.

Licence

Apache 2.0, inherited from the Qwen2.5 base model.

Downloads last month: 19

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for samaruban-v/astra-3b-tutor

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Quantized

(267)

this model