You can now run the Qiskit Code Assistant locally easily. Download optimized models in GGUF format, install Ollama, and configure your VSCode or JupyterLab extension with a single command.
The Curry–Howard correspondence—propositions as types, proofs as programs—offers a conceptual framework for understanding what's missing in current LLMs and what becomes possible when AI systems learn to construct and verify proofs natively.
We've upgraded the Qiskit Code Assistant! Last month, we introduced mistral-small-3.2-24b-qiskit, replacing granite-3.3-8b-qiskit, delivering better accuracy across key benchmarks and more precise responses for quantum programming tasks.
The qiskit-ibm-transpiler library advanced to `#3` in the Unitary Foundation 2025 Survey for full-stack development platforms, surpassing 929K downloads in under two years. AI transpiler passes now run in local mode without requiring an IBM Quantum premium plan.
David Peral García successfully defended his PhD thesis on Quantum Natural Language Processing, representing likely the first PhD thesis in Spain dedicated to this emerging field. A proud moment as my first doctoral thesis as an advisor.
Thrilled to have been a keynote speaker at Metafuturo 2025, sharing insights on the convergence of Quantum Computing and AI. From LLMs and agentic AI applications for quantum computing to AI-optimized quantum circuits at IBM Quantum.
Attending IEEE Quantum Week in Albuquerque, New Mexico, sharing IBM Quantum's work at the intersection of AI and Quantum Computing. Presenting on QPU time prediction with ML, AI methods for quantum circuit optimization, and demoing AI-powered quantum development environments.
Released a new paper on a novel approach to train AI models that can write better quantum code using Qiskit. The approach uses quantum verification at the core, smart training pipeline with DPO and GRPO, and real quantum feedback to ensure generated code works in practice.
Celebrating the impact of AI transpiler passes on IBM's quantum hardware achievements. Our team's work on AI-powered transpilation helped enable quantum volume milestones of 1024 and 2048 on IBM's r3 beta QPU (ibm_pittsburgh).
Announcing the latest open-source LLM releases from the Qiskit Code Assistant team, featuring Qiskit 2.0 compatibility, enhanced text understanding, and new models including Granite 3.3, Granite 3.2, and Qwen2.5-Coder series.