Qiskit/Qwen2.5-Coder-14B-Qiskit
TEXT GENERATIONConcurrency Cost:1Model Size:14.8BQuant:FP8Ctx Length:32kPublished:May 26, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Qwen-2.5-Coder-14B-Qiskit is a 14.7 billion parameter causal language model developed by Qiskit, based on the Qwen2.5-Coder architecture. Specialized in Qiskit coding, it offers significant improvements in code generation, reasoning, and fixing, trained with Qiskit version 2.0. This model supports a long context of up to 128K tokens and is designed for real-world applications like Code Agents, while maintaining strong mathematical and general competencies.

Loading preview...