Instructions to use AGofficial/minai-flash-lite-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AGofficial/minai-flash-lite-1b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AGofficial/minai-flash-lite-1b",
	filename="minai-flash-lite-1b.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use AGofficial/minai-flash-lite-1b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AGofficial/minai-flash-lite-1b
# Run inference directly in the terminal:
llama-cli -hf AGofficial/minai-flash-lite-1b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AGofficial/minai-flash-lite-1b
# Run inference directly in the terminal:
llama-cli -hf AGofficial/minai-flash-lite-1b

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/minai-flash-lite-1b
# Run inference directly in the terminal:
./llama-cli -hf AGofficial/minai-flash-lite-1b

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/minai-flash-lite-1b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AGofficial/minai-flash-lite-1b

Use Docker

docker model run hf.co/AGofficial/minai-flash-lite-1b

LM Studio
Jan
Ollama
How to use AGofficial/minai-flash-lite-1b with Ollama:
```
ollama run hf.co/AGofficial/minai-flash-lite-1b
```

Unsloth Studio new

How to use AGofficial/minai-flash-lite-1b 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/minai-flash-lite-1b 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/minai-flash-lite-1b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AGofficial/minai-flash-lite-1b to start chatting

Docker Model Runner
How to use AGofficial/minai-flash-lite-1b with Docker Model Runner:
```
docker model run hf.co/AGofficial/minai-flash-lite-1b
```

Lemonade

How to use AGofficial/minai-flash-lite-1b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AGofficial/minai-flash-lite-1b

Run and chat with the model

lemonade run user.minai-flash-lite-1b-{{QUANT_TAG}}

List all available models

lemonade list

Minai Flash Lite 1B

A lightweight, locally-runnable conversational AI packaged for instant use.

What is Minai Flash Lite 1B?

Minai Flash Lite 1B is a ready-to-run GGUF model that delivers fast, capable conversational AI on consumer hardware with just a single file and a Python script.

Designed to run entirely offline on your local machine — no cloud, no API keys, no data leaving your device.

File	Description
`minai-flash-lite-1b.gguf`	The model in GGUF format (float16). ~2 GB.
`chat.py`	Interactive CLI chat script with streaming output.
`README.md`	This file.

Requirements

Python 3.10+
llama-cpp-python with Metal support (for Apple Silicon GPU acceleration)

Install `llama-cpp-python` with Metal (Apple Silicon)

CMAKE_ARGS="-DGGML_METAL=on" pip install llama-cpp-python

Linux with NVIDIA GPU: Use CMAKE_ARGS="-DGGML_CUDA=on" instead. CPU-only: Just run pip install llama-cpp-python.

Run the Chat

python3 chat.py

You'll see a styled terminal interface. Start chatting immediately.

Chat commands:

/reset — Clear the conversation history
/exit — Quit the chat

Running on Other Platforms

The GGUF file is compatible with any llama.cpp-based runtime:

LM Studio — Drop the .gguf file in and chat via GUI.
Ollama — Import the GGUF and run via CLI.
Jan — Desktop app for local LLMs.
llama.cpp — Low-level CLI inference. jeminai

Downloads last month: 143

GGUF

Model size

1.0B 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

AGofficial
/

minai-flash-lite-1b

Minai Flash Lite 1B

What is Minai Flash Lite 1B?

Contents

Requirements

Install `llama-cpp-python` with Metal (Apple Silicon)

Run the Chat

Running on Other Platforms

Minai Flash Lite 1B

What is Minai Flash Lite 1B?

Contents

Requirements

Install llama-cpp-python with Metal (Apple Silicon)

Run the Chat

Running on Other Platforms

Install `llama-cpp-python` with Metal (Apple Silicon)