Instructions to use Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-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 Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K

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 Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K

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 Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K

Use Docker

docker model run hf.co/Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K

LM Studio
Jan

vLLM

How to use Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-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": "Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K

Ollama
How to use Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF with Ollama:
```
ollama run hf.co/Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K
```
Unsloth Desktop
Docker Model Runner
How to use Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF with Docker Model Runner:
```
docker model run hf.co/Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K
```

Lemonade

How to use Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF:Q6_K

Run and chat with the model

lemonade run user.Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF-Q6_K

List all available models

lemonade list

Atomic Chat

Model quantized with llama.cpp to Q6_K.

Original:

https://huggingface.co/speakleash/Bielik-4.5B-v3.0-Instruct

Same licence and terms of use as to the original applies. For info, please look at the original model page.

Downloads last month: 39

GGUF

Model size

5B params

Architecture

llama

Hardware compatibility

6-bit

Model tree for Wojtekb30/Bielik-4.5B-v3.0-Instruct-Q6_K-GGUF

Base model

speakleash/Bielik-4.5B-v3

Finetuned

speakleash/Bielik-4.5B-v3.0-Instruct

Quantized

(14)

this model