Instructions to use AGofficial/AgGPT-270M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AGofficial/AgGPT-270M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AGofficial/AgGPT-270M",
	filename="aggpt-270m.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AGofficial/AgGPT-270M with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AGofficial/AgGPT-270M
# Run inference directly in the terminal:
llama-cli -hf AGofficial/AgGPT-270M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AGofficial/AgGPT-270M
# Run inference directly in the terminal:
llama-cli -hf AGofficial/AgGPT-270M

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 AGofficial/AgGPT-270M
# Run inference directly in the terminal:
./llama-cli -hf AGofficial/AgGPT-270M

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 AGofficial/AgGPT-270M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AGofficial/AgGPT-270M

Use Docker

docker model run hf.co/AGofficial/AgGPT-270M

LM Studio
Jan
Ollama
How to use AGofficial/AgGPT-270M with Ollama:
```
ollama run hf.co/AGofficial/AgGPT-270M
```

Unsloth Studio

How to use AGofficial/AgGPT-270M 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 AGofficial/AgGPT-270M 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 AGofficial/AgGPT-270M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AGofficial/AgGPT-270M to start chatting

Docker Model Runner
How to use AGofficial/AgGPT-270M with Docker Model Runner:
```
docker model run hf.co/AGofficial/AgGPT-270M
```

Lemonade

How to use AGofficial/AgGPT-270M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AGofficial/AgGPT-270M

Run and chat with the model

lemonade run user.AgGPT-270M-{{QUANT_TAG}}

List all available models

lemonade list

AgGPT-270M

AgGPT-270M is a compact assistant model packaged as a standalone GGUF file.

Files

aggpt-270m.gguf - the ready-to-run GGUF model
chat.py - a small interactive Python chat script
SHA256SUMS.txt - checksum for the model file

Quick Start

The model file is self-contained, but you need a GGUF runtime to run it.

Option 1, Python:

python3 -m pip install llama-cpp-python
python3 chat.py

Option 2, llama.cpp CLI:

LLAMA_CLI=/path/to/llama.cpp/build/bin/llama-cli python3 chat.py

Then type messages at the prompt. Use /exit or Ctrl-C to quit.

Model Info

File: aggpt-270m.gguf
Format: GGUF, F16
Context: 32768 tokens
SHA-256: 1eecd1912d991a33e92665d17127b2ed60c06244a1920ca130b7fe7d0485bd58

Downloads last month: 152

GGUF

Model size

0.3B params

Architecture

gemma3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support