Instructions to use RaspizdAI/femboyAV-4b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RaspizdAI/femboyAV-4b-gguf 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 RaspizdAI/femboyAV-4b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RaspizdAI/femboyAV-4b-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RaspizdAI/femboyAV-4b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RaspizdAI/femboyAV-4b-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf RaspizdAI/femboyAV-4b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf RaspizdAI/femboyAV-4b-gguf:Q4_K_M

Use Docker

docker model run hf.co/RaspizdAI/femboyAV-4b-gguf:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use RaspizdAI/femboyAV-4b-gguf with Ollama:
```
ollama run hf.co/RaspizdAI/femboyAV-4b-gguf:Q4_K_M
```
Unsloth Desktop

How to use RaspizdAI/femboyAV-4b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RaspizdAI/femboyAV-4b-gguf:Q4_K_M

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": "RaspizdAI/femboyAV-4b-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use RaspizdAI/femboyAV-4b-gguf with Docker Model Runner:
```
docker model run hf.co/RaspizdAI/femboyAV-4b-gguf:Q4_K_M
```

Lemonade

How to use RaspizdAI/femboyAV-4b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RaspizdAI/femboyAV-4b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.femboyAV-4b-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use RaspizdAI/femboyAV-4b-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RaspizdAI/femboyAV-4b-gguf: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 RaspizdAI/femboyAV-4b-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RaspizdAI/femboyAV-4b-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RaspizdAI/femboyAV-4b-gguf: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 "RaspizdAI/femboyAV-4b-gguf: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"

femboyAV-4b GGUF

GGUF conversions of RaspizdAI/femboyAV-4b (an Unsloth LoRA fine-tune, 1 epoch, of Qwen3-VL-4B-Instruct-abliterated on the RaspizdAI/femboy-10k chat dataset; 10,000 public pairs out of the 10,330 used for training).

file	quantization	size
`model-f16.gguf`	F16	~7.7 GB
`model-q8_0.gguf`	Q8_0	~4.0 GB
`model-q4_k_m.gguf`	Q4_K_M	~2.3 GB
`mmproj-F16.gguf`	vision projector (F16)	~0.8 GB

The vision projector is unchanged from the base model, so mmproj-F16.gguf enables image input for all three quantizations.

Usage with llama.cpp

Text only:

llama-cli -m model-q8_0.gguf -p "Привет! Как дела?" -n 128

Server with vision:

llama-server -m model-q8_0.gguf -mm mmproj-F16.gguf --host 0.0.0.0 --port 8080

Then use the OpenAI-compatible API:

curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"role":"user","content":"Привет!"}],"max_tokens":128}'