Instructions to use dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF",
	filename="JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill.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 dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-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 dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-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 dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M

Use Docker

docker model run hf.co/dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-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": "dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M

Ollama
How to use dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF with Ollama:
```
ollama run hf.co/dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M
```

Unsloth Studio

How to use dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-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 dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-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 dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF to start chatting

How to use dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-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": "dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-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 dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF with Docker Model Runner:
```
docker model run hf.co/dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M
```

Lemonade

How to use dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF-Q4_K_M

List all available models

lemonade list

JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GUFF

This repository contains the GGUF quantized formats of JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF.

Model Overview

This model is a highly specialized fine-tune of Gemma-4-31B-it focused extensively on the Luau programming language (native to Roblox). It was developed using Quantization-Aware Distillation (QAD) methodologies and distilled using high-quality coding trajectories generated from Claude Opus, providing state-of-the-art zero-shot capabilities for Luau game development, bug resolution, and architectural design.

Key Features

Luau Specialization: Deep contextual understanding of Roblox Client/Server architecture, RemoteEvents, Task library semantics, and Modern UI (e.g., GuiObject layout hierarchies).
High-Quality Distillation: Distilled entirely from Claude Opus trajectories, inheriting advanced chain-of-thought and step-by-step reasoning structures.
GGUF Ready: Provided in standard GGUF format for optimal CPU/GPU offloading using llama.cpp, text-generation-webui, and Ollama.

Included Files

JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill.Q8.gguf (8-bit quantization, great quality and great performance).
JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill.Q4_K_M.gguf (4-bit quantization suitable for machines with limited VRAM).

Usage with `llama.cpp`

You can run the model directly inside a local environment using llama.cpp:

# Example using the Q8_0 quant
./main -m JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill.Q8_0.gguf \
  --color \
  -c 32768 \
  --temp 0.6 \
  -p "<bos><start_of_turn>user\nWrite a robust Luau character sprinting script with Server/Client validation.<end_of_turn>\n<start_of_turn>model\n"

Note: Ensure your context window (-c) is set appropriately for your available VRAM, as this model supports Gemma 4's extended context length.

Intended Use & Limitations

Intended Use: AI assistance for Roblox game development, script generation, syntax validation, and modular architecture planning.
Limitations: While strictly focused on Luau, the model may occasionally hallucinate standard Lua 5.1/5.4 functions that are disabled or heavily modified in Roblox's sandboxed environment (like loadstring without appropriate flags, or specific os functions).

Training Infrastructure

Fine-tuned on the NVIDIA RTX Pro 6000 Blackwell workstation using the Unsloth library.

Training

Time: The model was trained on 1x RTX Pro 6000 Blackwell 96GB Workstation Edition over the course of 20 hours with a high LoRA rank of 32 for enhanced logical throughput.

License

This model inherits the license of the base model [Google Gemma-4] and follows responsible AI distillation guidelines from Anthropic.

Downloads last month: 134

GGUF

Model size

31B params

Architecture

gemma4

Hardware compatibility

4-bit

8-bit

Model tree for dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Finetuned

unsloth/gemma-4-31B-it

Finetuned

TeichAI/gemma-4-31B-it-Claude-Opus-Distill

Quantized

TeichAI/gemma-4-31B-it-Claude-Opus-Distill-GGUF

Quantized

(1)

this model

dylanjkl
/

JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF

JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GUFF

Model Overview

Key Features

Included Files

Usage with `llama.cpp`

Intended Use & Limitations

Training Infrastructure

Training

License

Model tree for dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF

Datasets used to train dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF

JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GUFF

Model Overview

Key Features

Included Files

Usage with llama.cpp

Intended Use & Limitations

Training Infrastructure

Training

License

Model tree for dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF

Datasets used to train dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF

Usage with `llama.cpp`