Qiskit Code Assistant
A family of LLMs (8B–24B parameters) specialized for quantum code generation. Models built on IBM Granite, Mistral, and Qwen foundations, fine-tuned on curated Qiskit datasets including Python scripts, Jupyter notebooks, and synthetic Q&A pairs.
Open-source model family:
- Mistral Small 24B — Largest model, highest accuracy
- Qwen2.5 Coder 14B — Strong coding foundation
- Granite 3.x 8B — Efficient, multiple versions
- GGUF quantized versions available for local deployment
Achieves 46.53% on Qiskit HumanEval—significantly outperforming competing models (24.75%–39.6%). Supports natural language to code (“define a Bell circuit and run it on ibm_brisbane”) and intelligent autocomplete.
We created and open-sourced Qiskit HumanEval and Qiskit HumanEval Hard—benchmarks with 150+ tasks each, now used industry-wide for evaluating quantum code LLMs. Integrated into VS Code and JupyterLab.
I research and develop AI-based systems to tackle complex problems in quantum computing and other relevant areas.
My work sits at the intersection of quantum computing, machine learning, and open source. I hold IBM Master Inventor status and have contributed to tools used by millions of developers worldwide.
I have a PhD in Computer Engineering from the University of Salamanca (2018), have authored 80+ publications, and received the 2019 SCIE-BBVA Award for best young researcher in Computer Science in Spain.