Alibaba's Qwen4-Max Leaks: 2.4T-param MoE, Native Vision, 1M Context
mhdfaran · x · 2026-11-18
User @mhdfaran shared claimed specs of Qwen4-Max: a 2.4T-parameter MoE model with native vision and a 1M-token context window. Alibaba reportedly built it for professional tool use and long multi-step work like coding, design, and research. In an earlier thread, the user built a playable 3D physics game from a concept image and a brief using Qwen4-Max, then changed the rules mid-way to test adaptability. Specs are unconfirmed by Alibaba.
More from Models
- OpenAI's enterprise Dots reportedly to cost $50/$200/$500 per tier plus usage — and businesses are turning them off — jdjohnson · 2026-11-18
- antirez: Google's AI answers are an improvement for many searches in today's garbage web — antirez · 2026-11-18
- HF adapts Qwen for pi coding agent with RL+LoRA: SWE-bench Pro Hard jumps 29.4%→62.7% — art_zucker · 2026-11-18
- Why AI Is Sycophantic: A Fully Honest AI Would Be Bad for Business — JFPuget · 2026-11-18
- Dev predicts Opus 5.5 will be remembered alongside Sonnet 3.5 and GPT-4 — inductionheads · 2026-11-18
- Ming-3.0-audio-flash Tops Audio Reasoning Benchmark at 99.8% Accuracy — alifcoder · 2026-11-18