Instructions to use smehdia/maiui_8b_llamacpp_quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use smehdia/maiui_8b_llamacpp_quantized 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 smehdia/maiui_8b_llamacpp_quantized:Q8_0
# Run inference directly in the terminal:
llama cli -hf smehdia/maiui_8b_llamacpp_quantized:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf smehdia/maiui_8b_llamacpp_quantized:Q8_0
# Run inference directly in the terminal:
llama cli -hf smehdia/maiui_8b_llamacpp_quantized:Q8_0

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 smehdia/maiui_8b_llamacpp_quantized:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf smehdia/maiui_8b_llamacpp_quantized:Q8_0

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 smehdia/maiui_8b_llamacpp_quantized:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf smehdia/maiui_8b_llamacpp_quantized:Q8_0

Use Docker

docker model run hf.co/smehdia/maiui_8b_llamacpp_quantized:Q8_0

LM Studio
Jan
Ollama
How to use smehdia/maiui_8b_llamacpp_quantized with Ollama:
```
ollama run hf.co/smehdia/maiui_8b_llamacpp_quantized:Q8_0
```
Unsloth Desktop

How to use smehdia/maiui_8b_llamacpp_quantized with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smehdia/maiui_8b_llamacpp_quantized:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "smehdia/maiui_8b_llamacpp_quantized:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use smehdia/maiui_8b_llamacpp_quantized with Docker Model Runner:
```
docker model run hf.co/smehdia/maiui_8b_llamacpp_quantized:Q8_0
```

Lemonade

How to use smehdia/maiui_8b_llamacpp_quantized with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull smehdia/maiui_8b_llamacpp_quantized:Q8_0

Run and chat with the model

lemonade run user.maiui_8b_llamacpp_quantized-Q8_0

List all available models

lemonade list

Hermes Agent

How to use smehdia/maiui_8b_llamacpp_quantized with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smehdia/maiui_8b_llamacpp_quantized:Q8_0

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 smehdia/maiui_8b_llamacpp_quantized:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use smehdia/maiui_8b_llamacpp_quantized with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smehdia/maiui_8b_llamacpp_quantized:Q8_0

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 "smehdia/maiui_8b_llamacpp_quantized:Q8_0" \
  --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"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

MAI-UI-8B Server Deployment Package

OpenAI-compatible vision API for MAI-UI-8B (Q4_K_M + mmproj).

Path	Purpose
`bin/llama-server`	CUDA-built inference server
`bin/lib.so`	Required shared libraries
`models/*.gguf`	Quantized weights + vision projector
`start_server.sh`	Launch script

Requirements (target machine)

Linux x86_64
NVIDIA GPU with CUDA 12+ drivers (built for RTX 50-series / sm_120)
~11 GB VRAM for inference (16 GB GPU recommended)

Start

chmod +x start_server.sh
CUDA_VISIBLE_DEVICES=0 ./start_server.sh

API: http://localhost:8080/v1

Verify

curl http://localhost:8080/v1/models

Client

Point agents at http://<host>:8080/v1 with model_name matching the served GGUF name.

Downloads last month: 12

GGUF

Model size

8B params

Architecture

qwen3vl

Hardware compatibility

4-bit

Inference Providers NEW

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

smehdia
/

maiui_8b_llamacpp_quantized

MAI-UI-8B Server Deployment Package

Contents

Requirements (target machine)

Start

Verify

Client