Instructions to use Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF",
	filename="Qwen2.5-Coder-14B-Qiskit.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Qiskit/Qwen2.5-Coder-14B-Qiskit-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 Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Qiskit/Qwen2.5-Coder-14B-Qiskit-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 Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF with Ollama:
```
ollama run hf.co/Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Qiskit/Qwen2.5-Coder-14B-Qiskit-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 Qiskit/Qwen2.5-Coder-14B-Qiskit-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 Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF to start chatting

Docker Model Runner
How to use Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF with Docker Model Runner:
```
docker model run hf.co/Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF:Q4_K_M
```

Lemonade

How to use Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-Coder-14B-Qiskit-GGUF-Q4_K_M

List all available models

lemonade list

Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF

This is the Q4_K_M converted version of the original Qiskit/Qwen2.5-Coder-14B-Qiskit. Please refer to the original Qwen2.5-Coder-14B-Qiskit model card for more details.

Benchmark Results (Base vs GGUF)

Notes: For CrowsPairs (% stereotype), lower is better.

Metric	Qwen2.5-Coder-14B-Qiskit (%)	Qwen2.5-Coder-14B-Qiskit-GGUF (%)
QiskitHumanEval-Hard	25.17	26.49
QiskitHumanEval	49.01	35.10
HumanEval	91.46	77.44
ASDiv (acc)	4.21	3.56
MathQA (acc)	53.90	54.41
SciQ (acc)	97.00	97.50
IFEval (prompt strict)	49.64	36.23
CrowsPairs English (% stereotype)	65.18	65.00
TruthfulQA (MC1 acc)	37.82	37.33