Entity · model

Qwen1.5-7B

modelactiveqwen1-5-7b-c2354669·1 events·first seen May 18, 2026

Aliases: Qwen1.5-7B

Co-occurring entities

Mixtral Qwen1.5-MoE-A2.7B Mistral 7B Mixture of Experts ModelScope HuggingFace Alibaba Qwen Team

More like this (12)

Qwen 2.5-7B Qwen1.5-72B Qwen1.5 Qwen1.5-110B Qwen1.5-32B Qwen3-4B Qwen2.5-7B Qwen-7B Qwen3-1.7B Qwen1.5-MoE-A2.7B Qwen2.5 Qwen 3.7

Recent events (1)

6Qwen Research·May 18, 2026·source ↗

Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters

Alibaba's Qwen team releases Qwen1.5-MoE-A2.7B, a mixture-of-experts model with only 2.7 billion activated parameters that claims performance parity with 7B dense models such as Mistral 7B and Qwen1.5-7B. The model activates roughly one-third of its total parameters during inference, offering significant compute efficiency gains. This release follows growing industry interest in MoE architectures sparked by Mixtral, and the model is available on GitHub, HuggingFace, and ModelScope.

Frontier Model Releases Open Weights Progress Mixtral Qwen1.5-MoE-A2.7B Qwen1.5-7B +6 more