Sebastian Raschka
Read post

A Few Notable Open-Weight Models This Week

A roundup of six notable open-weight model releases from the past week, with architecture notes on each. Highlights include Nanbeige 4.2 3B using looped depth sharing to double compute without extra memory, Laguna S 2.1 (118B sparse MoE with 8B active params and 1M-token context), Motif-3-Beta introducing Grouped Differential Latent Attention, Solar Open 2 (250B-A15B hybrid MoE by Upstage), Antares 1B (Cisco's cybersecurity-focused small model built on IBM Granite), and BTL-3 (a LoRA adapter for Qwen3.6-27B targeting coding agents). All six models are added to the author's LLM Architecture Gallery.

    #llm#mixture-of-experts#lora
Jul 26•4m read time•From sebastianraschka.com
Post cover image
4 Impressions
Sebastian Raschka's image
Sebastian Raschka

Sebastian Raschka's Blog offers insights, tutorials, and research updates on machine learning, deep ...

176 Followers

•

1.3K Upvotes

Would you recommend this post?

Copy link
WhatsApp
Facebook
X
New Squad
  • © 2026 Daily Dev Ltd.
  • Guidelines
  • Explore
  • Tags
  • Sources
  • Squads
  • Leaderboard