Instructions to use chimbiwide/Gemma3NPC-Q4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chimbiwide/Gemma3NPC-Q4-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("chimbiwide/Gemma3NPC-Q4-GGUF", dtype="auto")

llama-cpp-python

How to use chimbiwide/Gemma3NPC-Q4-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="chimbiwide/Gemma3NPC-Q4-GGUF",
	filename="gemma3npc-q4_k_m.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use chimbiwide/Gemma3NPC-Q4-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf chimbiwide/Gemma3NPC-Q4-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf chimbiwide/Gemma3NPC-Q4-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 chimbiwide/Gemma3NPC-Q4-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf chimbiwide/Gemma3NPC-Q4-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 chimbiwide/Gemma3NPC-Q4-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf chimbiwide/Gemma3NPC-Q4-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 chimbiwide/Gemma3NPC-Q4-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf chimbiwide/Gemma3NPC-Q4-GGUF:Q4_K_M

Use Docker

docker model run hf.co/chimbiwide/Gemma3NPC-Q4-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use chimbiwide/Gemma3NPC-Q4-GGUF with Ollama:
```
ollama run hf.co/chimbiwide/Gemma3NPC-Q4-GGUF:Q4_K_M
```

Unsloth Studio new

How to use chimbiwide/Gemma3NPC-Q4-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 chimbiwide/Gemma3NPC-Q4-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 chimbiwide/Gemma3NPC-Q4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for chimbiwide/Gemma3NPC-Q4-GGUF to start chatting

Docker Model Runner
How to use chimbiwide/Gemma3NPC-Q4-GGUF with Docker Model Runner:
```
docker model run hf.co/chimbiwide/Gemma3NPC-Q4-GGUF:Q4_K_M
```

Lemonade

How to use chimbiwide/Gemma3NPC-Q4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull chimbiwide/Gemma3NPC-Q4-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Gemma3NPC-Q4-GGUF-Q4_K_M

List all available models

lemonade list

Gemma3NPC-Q4-GGUF

The "base" model that delivers good general role-playing at great speed.

The Q4_K_M quantized version of Gemma3NPC-Float16. We trained this model as a rank-16 LoRA adapter with one epoch over pippa using a 40GB vRAM A100 in Google Colab. For this run, we employed a learning rate of 2e-5 and a total batch size of 1 and gradient accumulation steps of 16. A cosine learning rate scheduler was used with an 800-step warmup. With a gradient clipping of 0.4. Check out our training notebook here.

Here is a graph of the Step Training Loss, saved every 10 steps: