Qwen Releases 2.4T-Parameter Open-Weight MoE Model Qwen3.8
rohanpaul_ai · x · 2026-08-13
Alibaba's Qwen team has dropped a new open-weight mixture-of-experts (MoE) model, Qwen3.8-2.4T-A95B, on Hugging Face. The model boasts a massive 2.4 trillion total parameters, further expanding their open-source LLM lineup.
Related event: Alibaba Open-Sources 2.4T Parameter Flagship Model Qwen3.8-Max(18 posts)→
More from Models
- Grok 4.6 Goes Live Everywhere: 2x Usage in Cursor and Grok Build for Launch Week — heypearlai · 2026-08-13
- Ollama Confirms Computer Use Feature is in the Works — reach_vb · 2026-08-13
- Developer Predicts Grok Will Win Claude Users Citing xAI's Insane Shipping Speed — XFreeze · 2026-08-13
- AMD Announces Day 0 Support for Qwen3.8-2.4T Open-Weight Model — AccBalanced · 2026-08-13
- New Model Scores 55 on Rescaled AA Benchmark, Competitive but Disappointing — teortaxesTex · 2026-08-13
- LM Arena's Auto-Eval Tool Predicts New DeepSeek Model at Rank 41 — Unusual_Guidance2095 · 2026-08-13