Instructions to use IlyaGusev/saiga_llama3_8b_gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IlyaGusev/saiga_llama3_8b_gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="IlyaGusev/saiga_llama3_8b_gguf",
	filename="model-f16.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 IlyaGusev/saiga_llama3_8b_gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf IlyaGusev/saiga_llama3_8b_gguf:F16
# Run inference directly in the terminal:
llama-cli -hf IlyaGusev/saiga_llama3_8b_gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf IlyaGusev/saiga_llama3_8b_gguf:F16
# Run inference directly in the terminal:
llama-cli -hf IlyaGusev/saiga_llama3_8b_gguf:F16

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 IlyaGusev/saiga_llama3_8b_gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf IlyaGusev/saiga_llama3_8b_gguf:F16

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 IlyaGusev/saiga_llama3_8b_gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf IlyaGusev/saiga_llama3_8b_gguf:F16

Use Docker

docker model run hf.co/IlyaGusev/saiga_llama3_8b_gguf:F16

LM Studio
Jan

vLLM

How to use IlyaGusev/saiga_llama3_8b_gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IlyaGusev/saiga_llama3_8b_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": "IlyaGusev/saiga_llama3_8b_gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IlyaGusev/saiga_llama3_8b_gguf:F16

Ollama
How to use IlyaGusev/saiga_llama3_8b_gguf with Ollama:
```
ollama run hf.co/IlyaGusev/saiga_llama3_8b_gguf:F16
```

Unsloth Studio new

How to use IlyaGusev/saiga_llama3_8b_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 IlyaGusev/saiga_llama3_8b_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 IlyaGusev/saiga_llama3_8b_gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for IlyaGusev/saiga_llama3_8b_gguf to start chatting

Docker Model Runner
How to use IlyaGusev/saiga_llama3_8b_gguf with Docker Model Runner:
```
docker model run hf.co/IlyaGusev/saiga_llama3_8b_gguf:F16
```

Lemonade

How to use IlyaGusev/saiga_llama3_8b_gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull IlyaGusev/saiga_llama3_8b_gguf:F16

Run and chat with the model

lemonade run user.saiga_llama3_8b_gguf-F16

List all available models

lemonade list

Llama.cpp compatible versions of an original 8B model.

Download one of the versions, for example model-q4_K.gguf.

wget https://huggingface.co/IlyaGusev/saiga_llama3_8b_gguf/resolve/main/model-q4_K.gguf

Download interact_llama3_llamacpp.py

wget https://raw.githubusercontent.com/IlyaGusev/rulm/master/self_instruct/src/interact_llama3_llamacpp.py

How to run:

pip install llama-cpp-python fire

python3 interact_llama3_llamacpp.py model-q4_K.gguf

System requirements:

10GB RAM for q8_0 and less for smaller quantizations

Downloads last month: 2,851

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

2-bit

8-bit

16-bit

Dataset used to train IlyaGusev/saiga_llama3_8b_gguf

Spaces using IlyaGusev/saiga_llama3_8b_gguf 2

Collection including IlyaGusev/saiga_llama3_8b_gguf

Saiga GGUF

Collection

Russian fine-tunes of different base LLMs in the GGUF format compatible with llama.cpp • 8 items • Updated Apr 27, 2025 • 39