Instructions to use cudgk/qwen3-8b-backgammon-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cudgk/qwen3-8b-backgammon-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cudgk/qwen3-8b-backgammon-gguf",
	filename="qwen3-8b-backgammon-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use cudgk/qwen3-8b-backgammon-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 cudgk/qwen3-8b-backgammon-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cudgk/qwen3-8b-backgammon-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 cudgk/qwen3-8b-backgammon-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cudgk/qwen3-8b-backgammon-gguf: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 cudgk/qwen3-8b-backgammon-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cudgk/qwen3-8b-backgammon-gguf: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 cudgk/qwen3-8b-backgammon-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cudgk/qwen3-8b-backgammon-gguf:Q4_K_M

Use Docker

docker model run hf.co/cudgk/qwen3-8b-backgammon-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use cudgk/qwen3-8b-backgammon-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cudgk/qwen3-8b-backgammon-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cudgk/qwen3-8b-backgammon-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cudgk/qwen3-8b-backgammon-gguf:Q4_K_M

Ollama
How to use cudgk/qwen3-8b-backgammon-gguf with Ollama:
```
ollama run hf.co/cudgk/qwen3-8b-backgammon-gguf:Q4_K_M
```

Unsloth Studio

How to use cudgk/qwen3-8b-backgammon-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for cudgk/qwen3-8b-backgammon-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for cudgk/qwen3-8b-backgammon-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cudgk/qwen3-8b-backgammon-gguf to start chatting

How to use cudgk/qwen3-8b-backgammon-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cudgk/qwen3-8b-backgammon-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "cudgk/qwen3-8b-backgammon-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use cudgk/qwen3-8b-backgammon-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 cudgk/qwen3-8b-backgammon-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 cudgk/qwen3-8b-backgammon-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use cudgk/qwen3-8b-backgammon-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cudgk/qwen3-8b-backgammon-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 "cudgk/qwen3-8b-backgammon-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"

Docker Model Runner
How to use cudgk/qwen3-8b-backgammon-gguf with Docker Model Runner:
```
docker model run hf.co/cudgk/qwen3-8b-backgammon-gguf:Q4_K_M
```

Lemonade

How to use cudgk/qwen3-8b-backgammon-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cudgk/qwen3-8b-backgammon-gguf:Q4_K_M

Run and chat with the model

lemonade run user.qwen3-8b-backgammon-gguf-Q4_K_M

List all available models

lemonade list

Qwen3-8B Backgammon (GGUF)

A backgammon-domain fine-tune of Qwen/Qwen3-8B, packaged for llama.cpp. Answers backgammon questions (rules, checker play, cube theory, match equity, race formulas, engine/AI history) in Japanese and English.

バックギャモンのドメイン知識（ルール、チェッカープレイ、キューブ理論、マッチエクイティ、レース理論、BG AI史）に特化してファインチューンした Qwen3-8B です。日本語・英語の両方で応答します。

Files

File	Size	Description
`qwen3-8b-backgammon-q4_k_m.gguf`	~5.0 GB	Merged model (base + LoRA), Q4_K_M quantized. Single-file, ready to run

Usage (llama.cpp)

llama-server -m qwen3-8b-backgammon-q4_k_m.gguf

Chat template: standard Qwen3 (<|im_start|> ChatML). Non-thinking mode is recommended (enable_thinking=False / default template).

Training

Base: Qwen/Qwen3-8B (Apache 2.0)
Method: QLoRA (r=64, alpha=64) via Unsloth on Kaggle T4. Two stages: continued pretraining (~870k tokens of backgammon literature, 1 epoch, lr 5e-5) then SFT (5,000 instruction pairs, 74% Japanese / 26% English, 3 epochs, lr 2e-4, train-on-responses-only). Final SFT train loss 1.24.
Data: a curated backgammon corpus assembled from classic strategy literature, Usenet (rec.games.backgammon) archives, engine documentation, match-equity tables and probability references, plus programmatically generated worked examples (Thorp count, Janowski take points, MET lookups). The corpus itself is not redistributed.

Behaviour & limitations

Compared to the stock model, it correctly grounds backgammon terminology (e.g. identifies the Thorp count as Ed Thorp's race cube formula rather than guessing) and answers in a dense, no-fluff style in Japanese or English.
It does not reliably reproduce exact formulas or table values. Details of multi-step formulas (Thorp count adjustments, MET cell values, etc.) can be confabulated. Treat numeric output as unverified; use a reference or RAG for exact values.
8B-class general reasoning limits apply. Not a playing engine — it explains concepts; it does not compute best moves.

License & attribution

This fine-tuned model (the weights in this repository) is released under CC BY-NC 4.0 — personal, research and other non-commercial use is allowed; any commercial use is prohibited. 本リポジトリの重みは CC BY-NC 4.0 です。個人利用・研究利用は自由ですが、営利目的での利用（販売、有償サービスへの組み込み、収益化コンテンツでの利用等）は一切禁止します。

The base model Qwen/Qwen3-8B is licensed under Apache 2.0 by the Qwen team; that license continues to govern the base model as obtained from its original source. Built with Qwen. Fine-tuned and released by cudgk. Not affiliated with the Qwen team or Alibaba Cloud.

Downloads last month: 74

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for cudgk/qwen3-8b-backgammon-gguf

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Adapter

(1913)

this model