Alibaba Releases Qwen3.8-Max: 2.4T Parameters and 1M Context
FellMentKE · x · 2026-08-06
Alibaba and the Qwen team have introduced Qwen3.8-Max, their most capable flagship model to date.
- Architecture & Scale: Built on a cutting-edge Sparse MoE architecture, it features 2.4T total parameters but activates just 95B for massive efficiency.
- Context & Modality: Natively multimodal across vision and text, it supports a 1M token context window, capable of processing massive inputs like 200+ page documents or 100-hour streams.
- Agentic Capabilities: Designed for long-horizon task execution, it reportedly completed a 16-day real-world software engineering project independently and outperformed humans in the WWW2025 Multimodal Dialogue Intent Recognition Challenge.
Related event: Alibaba's Qwen3.8-Max tops agentic benchmark, open-sources next week(11 posts)→
More from Models
- Users report Gemini's memories can't actually be deleted even after wiping chat history — ThrowRA_Purpose2025 · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Argon edges out astra as daily driver, but Claude still wins heavy coding work — iruletheworldmo · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- RoboVista benchmark: Gemini-4 Argon hits 81.9% on robotics understanding — berkeley_ai · 2026-10-16
- Dev reports decision model jev beats gpt-6-luna on quality in real training pipeline — genmon · 2026-10-16