Instructions to use AuroraSystem/Clary-0.6-0.6B-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 AuroraSystem/Clary-0.6-0.6B-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 AuroraSystem/Clary-0.6-0.6B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AuroraSystem/Clary-0.6-0.6B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AuroraSystem/Clary-0.6-0.6B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AuroraSystem/Clary-0.6-0.6B-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 AuroraSystem/Clary-0.6-0.6B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AuroraSystem/Clary-0.6-0.6B-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 AuroraSystem/Clary-0.6-0.6B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AuroraSystem/Clary-0.6-0.6B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AuroraSystem/Clary-0.6-0.6B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use AuroraSystem/Clary-0.6-0.6B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AuroraSystem/Clary-0.6-0.6B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AuroraSystem/Clary-0.6-0.6B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AuroraSystem/Clary-0.6-0.6B-GGUF:Q4_K_M

Ollama
How to use AuroraSystem/Clary-0.6-0.6B-GGUF with Ollama:
```
ollama run hf.co/AuroraSystem/Clary-0.6-0.6B-GGUF:Q4_K_M
```

Unsloth Studio

How to use AuroraSystem/Clary-0.6-0.6B-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 AuroraSystem/Clary-0.6-0.6B-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 AuroraSystem/Clary-0.6-0.6B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AuroraSystem/Clary-0.6-0.6B-GGUF to start chatting

Docker Model Runner
How to use AuroraSystem/Clary-0.6-0.6B-GGUF with Docker Model Runner:
```
docker model run hf.co/AuroraSystem/Clary-0.6-0.6B-GGUF:Q4_K_M
```

Lemonade

How to use AuroraSystem/Clary-0.6-0.6B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AuroraSystem/Clary-0.6-0.6B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Clary-0.6-0.6B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Aurora Clary 0.6 — GGUF (llama.cpp / LM Studio / Ollama)

Квантованные версии модели Aurora Clary 0.6 (Qwen3-0.6B + LoRA + зрение) в GGUF для llama.cpp-экосистемы.

Файлы

Файл	Квант	Размер
`aurora-q4_k_m.gguf`	Q4_K_M	397 MB
`aurora-q5_k_m.gguf`	Q5_K_M	444 MB
`aurora-q8_0.gguf`	Q8_0	639 MB
`aurora-f16.gguf`	F16	1.2 GB
`mmproj-model-f16.gguf`	F16	177 MB	Vision (CLIP + проектор)

Запуск

llama.cpp CLI (текст + Vision)

llama-cli -m aurora-q4_k_m.gguf --mmproj mmproj-model-f16.gguf

LM Studio

Скачайте aurora-q4_k_m.gguf + mmproj-model-f16.gguf
Положи в одну папку
LM Studio найдет mmproj автоматически → появится кнопка загрузки картинок

Ollama (текст)

ollama create aurora -f Modelfile

Modelfile:

FROM ./aurora-q4_k_m.gguf

Тест (текст)

> Напиши факториал на Python
def factorial(n):
    if n == 0:
        return 1
    else:
        return n * factorial(n-1)

> Столица России?
Москва

> 17 * 6 = ?
102

Возможности

Текст RU/EN, инструкции, код, математика, суммаризация
Вижн: описание картинок (через mmproj)
Контекст от базы (Qwen3)
/think режим

Ограничения

Вижн OCR слабый
Вижн работает только в llama.cpp-экосистеме (llama.cpp, LM Studio, KoboldCpp)

Лицензия

Apache-2.0. База — Qwen3-0.6B (Apache-2.0).

English

Quantized versions of Aurora Clary 0.6 (Qwen3-0.6B + LoRA + vision) in GGUF for the llama.cpp ecosystem.

Files

File	Quant	Size
`aurora-q4_k_m.gguf`	Q4_K_M	397 MB
`aurora-q5_k_m.gguf`	Q5_K_M	444 MB
`aurora-q8_0.gguf`	Q8_0	639 MB
`aurora-f16.gguf`	F16	1.2 GB
`mmproj-model-f16.gguf`	F16	177 MB	Vision (CLIP + projector)

Run

llama.cpp CLI (text + Vision)

llama-cli -m aurora-q4_k_m.gguf --mmproj mmproj-model-f16.gguf

LM Studio

Download aurora-q4_k_m.gguf + mmproj-model-f16.gguf
Put them in one folder
LM Studio finds mmproj automatically → image upload button appears

Ollama (text)

ollama create aurora -f Modelfile

Modelfile:

FROM ./aurora-q4_k_m.gguf

Test (text)

> Write a Python factorial function
def factorial(n):
    if n == 0:
        return 1
    else:
        return n * factorial(n-1)

> Capital of Russia?
Moscow

> 17 * 6 = ?
102

Capabilities

Text RU/EN, instructions, code, math, summarization
Vision: image description (via mmproj)
Context from base (Qwen3)
/think mode

Limitations

Vision OCR is weak
Vision works only in llama.cpp ecosystem (llama.cpp, LM Studio, KoboldCpp)

License

Apache-2.0. Base — Qwen3-0.6B (Apache-2.0).

Downloads last month: -

GGUF

Model size

0.6B params

Architecture

qwen3

Hardware compatibility

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for AuroraSystem/Clary-0.6-0.6B-GGUF

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Adapter

(515)

this model