Instructions to use Pauldyu57/gemma4-cnc-ll-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pauldyu57/gemma4-cnc-ll-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Pauldyu57/gemma4-cnc-ll-GGUF",
	filename="gemma4-cnc-ll-F16.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 Pauldyu57/gemma4-cnc-ll-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Pauldyu57/gemma4-cnc-ll-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Pauldyu57/gemma4-cnc-ll-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 Pauldyu57/gemma4-cnc-ll-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Pauldyu57/gemma4-cnc-ll-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 Pauldyu57/gemma4-cnc-ll-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Pauldyu57/gemma4-cnc-ll-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 Pauldyu57/gemma4-cnc-ll-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Pauldyu57/gemma4-cnc-ll-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Pauldyu57/gemma4-cnc-ll-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Pauldyu57/gemma4-cnc-ll-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pauldyu57/gemma4-cnc-ll-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": "Pauldyu57/gemma4-cnc-ll-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pauldyu57/gemma4-cnc-ll-GGUF:Q4_K_M

Ollama
How to use Pauldyu57/gemma4-cnc-ll-GGUF with Ollama:
```
ollama run hf.co/Pauldyu57/gemma4-cnc-ll-GGUF:Q4_K_M
```

Unsloth Studio

How to use Pauldyu57/gemma4-cnc-ll-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 Pauldyu57/gemma4-cnc-ll-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 Pauldyu57/gemma4-cnc-ll-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Pauldyu57/gemma4-cnc-ll-GGUF to start chatting

Docker Model Runner
How to use Pauldyu57/gemma4-cnc-ll-GGUF with Docker Model Runner:
```
docker model run hf.co/Pauldyu57/gemma4-cnc-ll-GGUF:Q4_K_M
```

Lemonade

How to use Pauldyu57/gemma4-cnc-ll-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Pauldyu57/gemma4-cnc-ll-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma4-cnc-ll-GGUF-Q4_K_M

List all available models

lemonade list

gemma4-cnc-ll (GGUF) — Two-stage Fine-tune

Two-stage QLoRA fine-tune of google/gemma-3-4b-it:

Stage 1 — Work-order knowledge CNC work-order database schema, BOM categories, pricing models, Neo4j/SQL queries for 永詮機械 (Yong Chuan Machinery).

Stage 2 — L&L 永詮 specialization (anti-dilution training) 14 machine models (LLA/LLB/LLS/LL/LFM/LFS/LS-C/LS-S/LS-U/LD/LC/TA/MA/LA/A), 6 application industries, company background. Trained with 5 anti-dilution mechanisms including critical-facts validation.

Quick start (Ollama)

ollama run hf.co/Pauldyu57/gemma4-cnc-ll-GGUF:Q4_K_M

Other tags: Q5_K_M, Q8_0, F16.

If this repo is private, link your Ollama SSH key first:

cat ~/.ollama/id_ed25519.pub
# → paste into https://huggingface.co/settings/keys

Files

Quant	Approx size	Notes
F16	~7.5 GB	Reference
Q8_0	~4.3 GB	Near-lossless
Q5_K_M	~3.0 GB	Good quality / size balance
Q4_K_M	~2.5 GB	Default for CPU / small GPUs

Base model

google/gemma-3-4b-it — usage subject to the Gemma Terms of Use.

Downloads last month: 372

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

4-bit

5-bit

8-bit

16-bit

Model tree for Pauldyu57/gemma4-cnc-ll-GGUF

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

(463)

this model