Instructions to use ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split 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 ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split: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 ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split:Q4_K_M

Use Docker

docker model run hf.co/ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split with Ollama:
```
ollama run hf.co/ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split:Q4_K_M
```
Unsloth Desktop

How to use ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split: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": "ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split with Docker Model Runner:
```
docker model run hf.co/ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split:Q4_K_M
```

Lemonade

How to use ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-4B-3D-Coder-GGUF-split-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split: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 ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split: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 "ReallyFloppyPenguin/Qwen3.5-4B-3D-Coder-GGUF-split: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"

Qwen3.5-4B-3D-Coder Q4_K_M (split GGUF)

The Q4_K_M GGUF from ccore/Qwen3.5-4B-3D-Coder, split into shards of 512 MB or less with llama-gguf-split. Browsers can't load a single file over 2 GB, so the split lets wllama run the model in-browser on WebGPU.

The weights are unchanged. All credit goes to ccore. See the original model card for usage, the system prompt and sampling settings.

Used by the 3D World Generator (WebGPU) Space.