Sebastian Raschka launches LLM Architecture Gallery covering 118 models with diff tool
rasbt · x · 2026-11-03
Sebastian Raschka reviews 10 open LLM architecture releases from October ("Open October"), including Kolibri-1 (78B, GQA+SWA), Ling 3.1 Flash (560B, Kimi Delta Attention), and models with gated MLA — and launches a curated LLM Architecture Gallery: 118 text-only LLM backbones with architecture diagrams, attention mechanisms, decoder types and fact sheets, a side-by-side architecture diff tool, a memory calculator, and a print-ready poster download. Open to corrections via GitHub issues.
Related event: Raschka Rounds Up 'Open October': 10 New Open LLM Architectures(2 posts)→
More from Models
- DeepMind RL-trained Gemini doubles correct psychiatric differential diagnoses in blind study — SRSchmidgall · 2026-11-04
- Particle-1 post-trained on DeepSeek V4.1 Flash cuts output tokens ~45% — heyneighbor · 2026-11-04
- Decider claims 1/10th of Jev's OpenRouter traffic in three weeks, leaderboard unverified — bo_wangbo · 2026-11-03
- Dev compares astra and sol to Opus 5.5: rigid on open-ended tasks — haider1 · 2026-11-03
- Open-source models now beat every 'frontier' model from just 11 months ago — Hesamation · 2026-11-03
- Sebastian Raschka Maps October's 'Open October': 10 Open LLM Architectures in One Month — rasbt · 2026-11-03