Qwen3.6-35B-A3B
Qwen3.6-35B-A3B is a large language model in Alibaba's Tongyi Qianwen series, with 35 billion parameters and a MoE architecture (A3B indicates 3 billion activated parameters). It supports local deployment.
Timeline (last 90 days)
The experiment uses the same Qwen 3.6-35B-A3B model, and the two versions with and without MTP have exactly the same number of parameters (35 billion parameters).
In the short question-answering test (a 400-character input plus a small question), the version with MTP reduced first-token latency from 5.9 seconds to 4.3 seconds, increased output speed from 57.98 characters/second to 66.14 characters/second (about 14% faster), and shortened the total time to finish the answer from 85.9 seconds to 62.3 seconds (27% faster).
A 35B model does not necessarily run faster than a 27B model, and if swap memory is used frequently, the experience may be worse than a smaller model.
All Facts (3)
The experiment uses the same Qwen 3.6-35B-A3B model, and the two versions with and without MTP have exactly the same number of parameters (35 billion parameters).
50%UnverifiedIn the short question-answering test (a 400-character input plus a small question), the version with MTP reduced first-token latency from 5.9 seconds to 4.3 seconds, increased output speed from 57.98 characters/second to 66.14 characters/second (about 14% faster), and shortened the total time to finish the answer from 85.9 seconds to 62.3 seconds (27% faster).
50%UnverifiedA 35B model does not necessarily run faster than a 27B model, and if swap memory is used frequently, the experience may be worse than a smaller model.
50%