Maxwell V1 Flash: open Apache-2.0 MoE (35B/A3B) targeting SE Asian languages

AdinaYakup · x · 2026-11-16

New team maxwell-model released Maxwell V1 Flash on Hugging Face: a MoE model with 35B total / 3B active parameters, 256K context, Apache 2.0 license. It focuses on multilinguality, especially Southeast Asian languages including Thai, Lao, Myanmar, Khmer, and Shan.

Related event: New team releases Maxwell V1 Flash MoE model focused on Southeast Asian languages(2 posts)→

Original post →

More from Models

Models channel →