Pinkstack/DistilGPT-OSS-qwen3-4B

Pinkstack/DistilGPT-OSS-qwen3-4B is a 4 billion parameter Qwen3-based model fine-tuned on GPT-OSS reasoning outputs, offering up to 262K tokens of total context. This model features adjustable reasoning effort (low, medium, high) and is optimized for efficient on-device assistance, code generation, and general day-to-day tasks. It provides a distinct answer style more akin to ChatGPT and produces fewer emojis compared to the original Qwen3 4B.