Qwen3-27B
An open-source large language model with 27.1 billion parameters released by Alibaba. It supports local deployment on consumer-grade hardware and possesses comprehensive capabilities in mathematics, coding, and research.
Timeline (last 90 days)
Qianwen 3-27B is a 27.1-billion-parameter model released in August 2026 that can run locally on a gaming laptop.
The third-party evaluation organization AI Mocha gave Qianwen 3-27B a score of 34 in a comprehensive test of math, code, and research abilities, while the champion of a year earlier, GPT-4o, scored only 23.
The current top model's comprehensive test score is 58, 24 points above Qianwen 3-27B's 34.
AI Mocha publicly released Qianwen 3-27B's full model weights, evaluation code, and research methods, so anyone can reproduce the results on their own hardware.
All Facts (4)
Qianwen 3-27B is a 27.1-billion-parameter model released in August 2026 that can run locally on a gaming laptop.
50%UnverifiedThe third-party evaluation organization AI Mocha gave Qianwen 3-27B a score of 34 in a comprehensive test of math, code, and research abilities, while the champion of a year earlier, GPT-4o, scored only 23.
50%UnverifiedThe current top model's comprehensive test score is 58, 24 points above Qianwen 3-27B's 34.
50%UnverifiedAI Mocha publicly released Qianwen 3-27B's full model weights, evaluation code, and research methods, so anyone can reproduce the results on their own hardware.
50%