Alibaba's Qwen 3.8-Max Activates Only 95B of 2.4T Parameters
Div_pradeep · x · 2026-08-05
Alibaba has reportedly released the Qwen 3.8-Max model. The model features a massive 2.4 trillion total parameters but activates only 95B during inference.
Thanks to this highly efficient Mixture-of-Experts (MoE) architecture, it ranks among the world's best frontier models, drawing attention for its impressive inference efficiency.
Related event: Alibaba Reportedly Launches Qwen 3.8-Max with 2.4T Parameters(2 posts)→
More from Models
- Don't Mythologize Unreleased Models: GPT Image 2 Already Delivers High Quality — Angaisb_ · 2026-08-05
- Qwen Devs AMA: 3.8 Model Hits 2.4T Params, 27B Version Coming Soon — pmttyji · 2026-08-05
- ChatGPT Swears Unprompted While Calculating Retirement Plans — Zikkan1 · 2026-08-05
- Qwen's FinIndices Benchmark Exposes Severe Bottlenecks in LLM Financial Reasoning — Qwen · 2026-08-05
- User Notes Claude Opus Drops Pleasantries for Blunt Direct Answers — CtrlAltDwayne · 2026-08-05
- Abliteration: Removing LLM Safety Guardrails Without Retraining is Now an Open-Source Standard — maximelabonne · 2026-08-05