Instructions to use Jzic/flower-war-voice with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Jzic/flower-war-voice 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 Jzic/flower-war-voice:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Jzic/flower-war-voice:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Jzic/flower-war-voice:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Jzic/flower-war-voice:Q4_K_M

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 Jzic/flower-war-voice:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Jzic/flower-war-voice:Q4_K_M

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 Jzic/flower-war-voice:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Jzic/flower-war-voice:Q4_K_M

Use Docker

docker model run hf.co/Jzic/flower-war-voice:Q4_K_M

LM Studio
Jan
Ollama
How to use Jzic/flower-war-voice with Ollama:
```
ollama run hf.co/Jzic/flower-war-voice:Q4_K_M
```
Unsloth Desktop

How to use Jzic/flower-war-voice with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Jzic/flower-war-voice: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": "Jzic/flower-war-voice:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Jzic/flower-war-voice with Docker Model Runner:
```
docker model run hf.co/Jzic/flower-war-voice:Q4_K_M
```

Lemonade

How to use Jzic/flower-war-voice with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Jzic/flower-war-voice:Q4_K_M

Run and chat with the model

lemonade run user.flower-war-voice-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Jzic/flower-war-voice with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Jzic/flower-war-voice: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 Jzic/flower-war-voice:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Jzic/flower-war-voice with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Jzic/flower-war-voice: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 "Jzic/flower-war-voice: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"

flower-war-voice

The councillors' voice for Flower War, a social deduction game set on the Aztec council in 1500. It speaks one short line in council for a councillor, from a brief the game writes: what happened, who is on the party, how the councillor stands and the mood asked for.

It is Qwen3-4B-Instruct-2507 with a LoRA fine-tune (the game's "mood" voice) fused into the weights and quantized to Q4_K_M, 2.3 GB. It is built for the game's own prompts and is not a general assistant.

Use

The game's Windows installer downloads it through Ollama:

ollama pull hf.co/Jzic/flower-war-voice:Q4_K_M

The repository's template and params are Ollama's own for qwen3:4b-instruct-2507, which is the chat format the fine-tune was trained on.

How it was made

tools/finetune/export_fused.sh in the game's repository: mlx_lm fuse --dequantize against the 4-bit MLX base the adapter was trained on, convert_hf_to_gguf.py, then llama-quantize Q4_K_M.

License

Downloads last month: 23

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for Jzic/flower-war-voice

Base model

Qwen/Qwen3-4B-Instruct-2507

Quantized

(340)

this model