#qwen

2 articles tagged

Dark data hall server racks with lit GPU slots, representing trillion-parameter model serving

AI & Cloud Infrastructure · Jul 22, 2026 · 14 min read

Qwen3.8-Max: 2.4T parameters, 1.2TB of VRAM, and the number Alibaba has not published

Qwen3.8-Max carries 2.4 trillion total parameters and needs roughly 1.2TB of VRAM at 4-bit. The number that decides whether you can run it, the active-parameter count, is the one Alibaba has not published.

Manu Shukla

#qwen #open weights #moe

3D render of a glowing server rack beside a downward cost curve on a dark studio background

AI & Cloud Infrastructure · Jul 9, 2026 · 10 min read

3 Chinese open models that cut enterprise AI bills 60-90% in 2026

US firms routed up to 46% of their OpenRouter tokens to Chinese open models in 2026 because they cost 60-90% less. Here is how DeepSeek, Qwen and GLM compare with OpenAI and Google on price, quality and risk.

Manu Shukla

#chinese ai models #DeepSeek #qwen