Instructions to use waqasm86/llcuda-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use waqasm86/llcuda-models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="waqasm86/llcuda-models",
	filename="google_gemma-3-1b-it-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use waqasm86/llcuda-models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf waqasm86/llcuda-models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf waqasm86/llcuda-models:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf waqasm86/llcuda-models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf waqasm86/llcuda-models: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 waqasm86/llcuda-models:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf waqasm86/llcuda-models: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 waqasm86/llcuda-models:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf waqasm86/llcuda-models:Q4_K_M

Use Docker

docker model run hf.co/waqasm86/llcuda-models:Q4_K_M

LM Studio
Jan

vLLM

How to use waqasm86/llcuda-models with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "waqasm86/llcuda-models"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "waqasm86/llcuda-models",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/waqasm86/llcuda-models:Q4_K_M

Ollama
How to use waqasm86/llcuda-models with Ollama:
```
ollama run hf.co/waqasm86/llcuda-models:Q4_K_M
```

Unsloth Studio new

How to use waqasm86/llcuda-models 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 waqasm86/llcuda-models 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 waqasm86/llcuda-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for waqasm86/llcuda-models to start chatting

Docker Model Runner
How to use waqasm86/llcuda-models with Docker Model Runner:
```
docker model run hf.co/waqasm86/llcuda-models:Q4_K_M
```

Lemonade

How to use waqasm86/llcuda-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull waqasm86/llcuda-models:Q4_K_M

Run and chat with the model

lemonade run user.llcuda-models-Q4_K_M

List all available models

lemonade list

llcuda Models

Optimized GGUF models for llcuda - Zero-config CUDA-accelerated LLM inference.

Models

google_gemma-3-1b-it-Q4_K_M.gguf

Model: Google Gemma 3 1B Instruct
Quantization: Q4_K_M (4-bit)
Size: 769 MB
Use case: General-purpose chat, Q&A, code assistance
Recommended for: 1GB+ VRAM GPUs

Performance:

Tesla T4 (Colab/Kaggle): ~15 tok/s
Tesla P100 (Colab): ~18 tok/s
GeForce 940M (1GB): ~15 tok/s
RTX 30xx/40xx: ~25+ tok/s

Usage

With llcuda (Recommended)

pip install llcuda

import llcuda
engine = llcuda.InferenceEngine()
engine.load_model("gemma-3-1b-Q4_K_M")
result = engine.infer("What is AI?")
print(result.text)

With llama.cpp

# Download model
huggingface-cli download waqasm86/llcuda-models google_gemma-3-1b-it-Q4_K_M.gguf --local-dir ./models

# Run with llama.cpp
./llama-server -m ./models/google_gemma-3-1b-it-Q4_K_M.gguf -ngl 26

Supported Platforms

✅ Google Colab (T4, P100, V100, A100)
✅ Kaggle (Tesla T4)
✅ Local GPUs (GeForce, RTX, Tesla)
✅ All NVIDIA GPUs with compute capability 5.0+

License

Apache 2.0 - Models are provided as-is for educational and research purposes.

Credits

Model: Google Gemma 3 1B
Quantization: llama.cpp GGUF format
Package: llcuda by Waqas Muhammad

Downloads last month: 15

GGUF

Model size

1.0B params

Architecture

gemma3

Hardware compatibility

4-bit

waqasm86
/

llcuda-models