Instructions to use skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF",
	filename="lapa-v0.1.3-instruct-Q8_0.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 skypro1111/lapa-v0.1.3-instruct-Q8_0-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 skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0

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 skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0

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 skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0

Use Docker

docker model run hf.co/skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "skypro1111/lapa-v0.1.3-instruct-Q8_0-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": "skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0

Ollama
How to use skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF with Ollama:
```
ollama run hf.co/skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0
```

Unsloth Studio

How to use skypro1111/lapa-v0.1.3-instruct-Q8_0-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 skypro1111/lapa-v0.1.3-instruct-Q8_0-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 skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0
```

Lemonade

How to use skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.lapa-v0.1.3-instruct-Q8_0-GGUF-Q8_0

List all available models

lemonade list

Lapa v0.1.3 Instruct — Q8_0 GGUF

8-bit (Q8_0) GGUF quantization of lapa-llm/lapa-v0.1.3-instruct — a Ukrainian-specialized instruction model built on Google's Gemma 3 12B, with roughly 80 000 of its 256 000 tokenizer tokens replaced by Ukrainian-oriented ones.

This repository contains only the quantized weights. For the original model, tokenizer sources, training details and intended use, see the upstream model card.

Files

File	Quant	Size	Notes
`lapa-v0.1.3-instruct-Q8_0.gguf`	`Q8_0`	~12.5 GB	Near-lossless 8-bit; fits a single 24 GB GPU

Why Q8_0

Q8_0 is the highest-fidelity common GGUF quant (8-bit, ~0.5 GB per B params). It keeps generation quality effectively indistinguishable from the bf16 original while roughly halving memory, so the full 12B model fits comfortably on one 24 GB card (e.g. RTX 3090/4090) with room for KV cache. This matters here because Lapa's modified tokenizer makes the model sensitive to precision loss — lower-bit quants (Q4/Q5/Q6) risk degrading Ukrainian morphology, so Q8_0 is the recommended operating point.

How it was made

Following the official Lapa quantization recipe, which uses a patched converter that preserves Lapa's custom tokenizer (tokenizer.model + merge_info.json) so no vocabulary precision is lost:

# llama.cpp @ b8185
# 1. HF safetensors -> F16 GGUF (patched Lapa converter)
python convert_hf_to_gguf_lapa.py lapa-v0.1.3-instruct/ \
    --outfile lapa-12B-it-F16.gguf --outtype f16

# 2. F16 -> Q8_0
llama-quantize lapa-12B-it-F16.gguf lapa-v0.1.3-instruct-Q8_0.gguf Q8_0

Usage

`llama-server` (OpenAI-compatible API)

llama-server \
  --model lapa-v0.1.3-instruct-Q8_0.gguf \
  --host 0.0.0.0 --port 8080 \
  --n-gpu-layers 999 --ctx-size 8192 --flash-attn on

curl http://127.0.0.1:8080/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"messages":[{"role":"user","content":"Розкажи коротко про місто Львів."}],
       "temperature":0.3}'

`llama-cli`

llama-cli -m lapa-v0.1.3-instruct-Q8_0.gguf -ngl 999 -c 8192 \
  -p "Перепиши речення без цифр: На 500 сторінках є примітки."

Download

huggingface-cli download skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF \
  lapa-v0.1.3-instruct-Q8_0.gguf --local-dir .

License

Derived from Google Gemma 3 and inherits the Gemma Terms of Use. Use of these weights is subject to those terms and to any terms of the upstream lapa-llm/lapa-v0.1.3-instruct model.

Credits

Original model: Lapa LLM team — lapa-llm/lapa-v0.1.3-instruct
Base architecture: Google Gemma 3
Quantization tooling: llama.cpp

This is an unofficial, community quantization. Not affiliated with the Lapa LLM team or Google.

Downloads last month: 101

GGUF

Model size

12B params

Architecture

gemma3

Hardware compatibility

8-bit

Model tree for skypro1111/lapa-v0.1.3-instruct-Q8_0-GGUF

Base model

google/gemma-3-12b-pt

Finetuned

lapa-llm/lapa-12b-pt