PulseAugur
LIVE 08:06:30
frontier release · [1 source] ·
0
frontier release

Alibaba's Qwen3.5-397B-A17B model offers multimodal capabilities and efficient inference

Alibaba has released Qwen3.5-397B-A17B, an open-weight, natively multimodal model featuring a hybrid attention mechanism and sparse Mixture-of-Experts architecture. The model boasts support for 201 languages and demonstrates significant improvements over its predecessors, particularly in vision tasks. Despite its large size, community efforts have enabled efficient local deployment on consumer hardware, though API pricing has drawn some criticism. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

RANK_REASON Open-weight model release from a major lab with significant architectural advancements.

Read on Smol AINews →

Alibaba's Qwen3.5-397B-A17B model offers multimodal capabilities and efficient inference

COVERAGE [1]

  1. Smol AINews TIER_1 ·

    Qwen3.5-397B-A17B: the smallest Open-Opus class, very efficient model

    **Alibaba** released **Qwen3.5-397B-A17B**, an open-weight model featuring **native multimodality**, **spatial intelligence**, and a **hybrid linear attention + sparse MoE** architecture supporting **201 languages** and **long context windows** up to **256K tokens**. The model sh…