Instructions to use SciTools/Qwen3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use SciTools/Qwen3 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="SciTools/Qwen3", filename="Qwen3-0.6B-Q4_K_M.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use SciTools/Qwen3 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf SciTools/Qwen3:Q4_K_M # Run inference directly in the terminal: llama-cli -hf SciTools/Qwen3:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf SciTools/Qwen3:Q4_K_M # Run inference directly in the terminal: llama-cli -hf SciTools/Qwen3: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 SciTools/Qwen3:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf SciTools/Qwen3: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 SciTools/Qwen3:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf SciTools/Qwen3:Q4_K_M
Use Docker
docker model run hf.co/SciTools/Qwen3:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use SciTools/Qwen3 with Ollama:
ollama run hf.co/SciTools/Qwen3:Q4_K_M
- Unsloth Studio new
How to use SciTools/Qwen3 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 SciTools/Qwen3 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 SciTools/Qwen3 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for SciTools/Qwen3 to start chatting
- Pi new
How to use SciTools/Qwen3 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf SciTools/Qwen3:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "SciTools/Qwen3:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use SciTools/Qwen3 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf SciTools/Qwen3:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default SciTools/Qwen3:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use SciTools/Qwen3 with Docker Model Runner:
docker model run hf.co/SciTools/Qwen3:Q4_K_M
- Lemonade
How to use SciTools/Qwen3 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull SciTools/Qwen3:Q4_K_M
Run and chat with the model
lemonade run user.Qwen3-Q4_K_M
List all available models
lemonade list
Qwen3 GGUF (4_K_M Quantized)
This repository hosts GGUF-format quantized versions of Qwen3 models at multiple parameter sizes.
All models are quantized at 4_K_M, selected to provide a practical balance of inference performance, memory usage, and output quality.
These files are intended for use with SciTools’ Understand and Onboard, as well as other tools and runtimes that support the GGUF format (for example, llama.cpp-based applications).
Model Details
- Base models: Qwen3 (various parameter sizes)
- Format: GGUF
- Quantization: 4_K_M
- Intended use: Local inference, code understanding, general-purpose chat
- Languages: Multilingual (as supported by Qwen3)
Available Variants
This repository includes multiple Qwen3 parameter sizes, each quantized independently but consistently using the same 4_K_M scheme. Refer to the file names for exact parameter counts.
Quantization Process
- All models are quantized using the 4_K_M quantization method.
- Quantization was performed directly by the Qwen team where available.
- In a small number of cases, quantization was performed by Unsloth.
- No further modifications, rebalancing, or fine-tuning were applied.
- The quantization parameters and defaults were not altered from the original sources.
The goal is to provide faithful, reproducible GGUF variants that behave as closely as possible to their upstream counterparts within the constraints of 4-bit quantization.
What We Did Not Do
To be explicit:
- No additional fine-tuning
- No instruction rebalancing
- No safety, alignment, or prompt modifications
- No merging or model surgery
If a model behaves a certain way, that behavior comes from Qwen3 combined with 4_K_M quantization, not from any downstream changes here.
Intended Use
These models are suitable for:
- SciTools Understand and SciTools Onboard
- Local AI workflows
- Code comprehension and exploration
- Interactive chat and analysis
- Integration into developer tools that support GGUF
They are not intended for:
- Safety-critical or regulated decision-making
- Use cases requiring guaranteed factual accuracy
- Production deployment without independent evaluation
Limitations
- As 4-bit quantized models, some degradation in reasoning depth and numerical precision is expected compared to full-precision checkpoints.
- Output quality varies by parameter size and task.
- Like all large language models, Qwen3 may produce hallucinations or incorrect information.
Evaluate carefully for your specific workload.
License & Attribution
- Original models: Qwen / Alibaba Cloud
- Quantization: Qwen and Unsloth
- Format: GGUF (llama.cpp ecosystem)
Please refer to the original Qwen3 license and usage terms. This repository redistributes quantized artifacts only and does not change the underlying licensing conditions.
Acknowledgements
Thanks to the Qwen team for releasing Qwen3 models and to Unsloth for high-quality, reproducible quantization tooling that enables efficient local inference across a wide range of tools.
- Downloads last month
- 61
4-bit
docker model run hf.co/SciTools/Qwen3:Q4_K_M