Alibaba Launches Qwen3.8-Max: 2.4T Parameter MoE with Native Multimodal
alifcoder · x · 2026-08-09
Alibaba has released Qwen3.8-Max, its most powerful flagship model to date. Built on a Sparse Mixture-of-Experts (MoE) architecture, the model features a total of 2.4T parameters with 95B active parameters.
Key Highlights:
- 1 million-token context window
- Native multimodal intelligence (vision + text)
- Advanced autonomous coding and long-horizon task execution
Qwen3.8-Max is now available globally via Alibaba Cloud Model Studio API, with open weights scheduled for release on Hugging Face next week.
Related event: Rumors Claim Alibaba Released Qwen3.8-Max(2 posts)→
More from Models
- Ornith-1.5 Open Models Released, Claiming Claude Opus Performance — alejandroll10 · 2026-08-26
- 14-year AI veteran: Grok understood code I thought no one ever would — Kuprel · 2026-08-26
- Together Ranks Top Open Models: Kimi K3 and DeepSeek V4 Lead Use Cases — togethercompute · 2026-08-26
- Questions over Astra's progress: 2 months for 3 more models? — teortaxesTex · 2026-08-26
- View: Tokens-per-second matters more than model size now — natesiggard · 2026-08-26
- Tiel-Coder-35B achieves 121.4 tok/s for local inference — DerTomsn · 2026-08-26