AGofficial/minai-flash-lite-1b

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.

---

Contents

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